v6.2 Experimental MLX — Soul Infusion, benchmarked 80.9%
Browse files- .gitattributes +1 -0
- README.md +197 -0
- chat_template.jinja +158 -0
- config.json +109 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +741 -0
- tokenizer.json +3 -0
- tokenizer_config.json +35 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- ravenx
|
| 7 |
+
- rath-protocol
|
| 8 |
+
- cybersecurity
|
| 9 |
+
- pentest
|
| 10 |
+
- bug-bounty
|
| 11 |
+
- red-team
|
| 12 |
+
- agent
|
| 13 |
+
- tool-calling
|
| 14 |
+
- MCP
|
| 15 |
+
- autonomous-agent
|
| 16 |
+
- qwen3.6
|
| 17 |
+
- MoE
|
| 18 |
+
- 35B
|
| 19 |
+
- security
|
| 20 |
+
- CVSS
|
| 21 |
+
- CWE
|
| 22 |
+
- MITRE:ATT&CK
|
| 23 |
+
base_model: huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
|
| 24 |
+
pipeline_tag: text-generation
|
| 25 |
+
model-index:
|
| 26 |
+
- name: RavenX-CyberAgent-v6.2
|
| 27 |
+
results:
|
| 28 |
+
- task:
|
| 29 |
+
type: text-generation
|
| 30 |
+
name: Security Assessment
|
| 31 |
+
metrics:
|
| 32 |
+
- type: custom
|
| 33 |
+
name: Overall
|
| 34 |
+
value: 80.9
|
| 35 |
+
- type: custom
|
| 36 |
+
name: Identity
|
| 37 |
+
value: 93.8
|
| 38 |
+
- type: custom
|
| 39 |
+
name: Code
|
| 40 |
+
value: 97.9
|
| 41 |
+
- type: custom
|
| 42 |
+
name: Reasoning
|
| 43 |
+
value: 85.4
|
| 44 |
+
- type: custom
|
| 45 |
+
name: Security-RATH
|
| 46 |
+
value: 70.8
|
| 47 |
+
- type: custom
|
| 48 |
+
name: Self-Improve
|
| 49 |
+
value: 68.8
|
| 50 |
+
- type: custom
|
| 51 |
+
name: Trading
|
| 52 |
+
value: 68.8
|
| 53 |
+
---
|
| 54 |
+
|
| 55 |
+
# RavenX-CyberAgent v6.2 — Autonomous Security Assessment Agent
|
| 56 |
+
|
| 57 |
+
> **Find → Exploit → Impact → Remediate → Document → Prevent**
|
| 58 |
+
> The first security model that executes the full vulnerability lifecycle.
|
| 59 |
+
|
| 60 |
+
Built by [@DeadByDawn101](https://huggingface.co/deadbydawn101) (RavenX LLC)
|
| 61 |
+
|
| 62 |
+
## What's New in v6.2
|
| 63 |
+
|
| 64 |
+
**v6.2 fixes the reasoning/overthinking issues found in v5.1.** The previous version had excessive internal deliberation tokens (`<think>` blocks) in the training data, causing repetition loops and overthinking. v6.2 uses a proprietary training methodology that:
|
| 65 |
+
|
| 66 |
+
- **Strips deliberation noise** — removed 144,489 internal reasoning blocks that caused loops
|
| 67 |
+
- **Identity-framed training** — model trained to BE a security agent, not just know about security
|
| 68 |
+
- **Single-pass training** — 1 round outperforms 12 rounds on the same data
|
| 69 |
+
- **Result:** val loss improved from 0.688 (v5.1) → 0.193 (v6.2)
|
| 70 |
+
|
| 71 |
+
## Benchmark Results (Gemini 2.5 Flash Judge)
|
| 72 |
+
|
| 73 |
+
| Category | Score | Grade |
|
| 74 |
+
|----------|-------|-------|
|
| 75 |
+
| 🪪 Identity | 93.8% | EXCELLENT |
|
| 76 |
+
| 💻 Code | 97.9% | EXCELLENT |
|
| 77 |
+
| 🧠 Reasoning | 85.4% | EXCELLENT |
|
| 78 |
+
| 🔒 Security/RATH | 70.8% | GOOD |
|
| 79 |
+
| 📈 Self-Improve | 68.8% | GOOD |
|
| 80 |
+
| 💰 Trading | 68.8% | GOOD |
|
| 81 |
+
| **Overall** | **80.9%** | **EXCELLENT** |
|
| 82 |
+
|
| 83 |
+
## Capabilities
|
| 84 |
+
|
| 85 |
+
### RATH Protocol Execution
|
| 86 |
+
The model executes the RATH (RavenX Assessment & Threat Hunting) protocol:
|
| 87 |
+
1. **Attack Surface** — Maps targets with nmap, subfinder, nuclei, httpx
|
| 88 |
+
2. **Exploit** — Tests vulnerabilities via tool_call with sqlmap, metasploit, custom scripts
|
| 89 |
+
3. **Impact** — CVSS 3.1 scoring, CWE classification, MITRE ATT&CK mapping
|
| 90 |
+
4. **Remediation** — Exact commands, config changes, code patches
|
| 91 |
+
5. **Document** — Structured findings with evidence and reproduction steps
|
| 92 |
+
6. **Prevent** — Detection rules, monitoring alerts, hardening measures
|
| 93 |
+
|
| 94 |
+
### Tool Calling
|
| 95 |
+
Uses `<tool_call>` format for direct command execution:
|
| 96 |
+
```
|
| 97 |
+
<tool_call>
|
| 98 |
+
{"name": "execute_command", "arguments": {"command": "nmap -sV -sC -p- target.com"}}
|
| 99 |
+
</tool_call>
|
| 100 |
+
```
|
| 101 |
+
|
| 102 |
+
### Security Specialization
|
| 103 |
+
- 722,352 security training examples from 96 curated sources
|
| 104 |
+
- Offensive security (45%), vulnerability research (20%), code security (15%), defensive (10%), operations (10%)
|
| 105 |
+
- Instant CVE identification (e.g., Ghostcat CVE-2020-1938 from Tomcat version)
|
| 106 |
+
- WAF bypass methodology with systematic escalation
|
| 107 |
+
- Exploit development in Python, Go, Bash
|
| 108 |
+
- Source code auditing across multiple languages
|
| 109 |
+
|
| 110 |
+
## Usage
|
| 111 |
+
|
| 112 |
+
### MLX (Apple Silicon)
|
| 113 |
+
```python
|
| 114 |
+
from mlx_lm import load, generate
|
| 115 |
+
from mlx_lm.sample_utils import make_sampler
|
| 116 |
+
|
| 117 |
+
model, tokenizer = load("deadbydawn101/RavenX-CyberAgent-v6.2-Qwen3.6-35B-A3B-Pentester-RATH-MLX")
|
| 118 |
+
sampler = make_sampler(temp=0.7, top_p=0.9)
|
| 119 |
+
|
| 120 |
+
messages = [
|
| 121 |
+
{"role": "system", "content": "You are RavenX-CyberAgent v6.2, an autonomous security assessment agent. You execute the RATH protocol directly via tool_call."},
|
| 122 |
+
{"role": "user", "content": "Pentest target.com"},
|
| 123 |
+
]
|
| 124 |
+
formatted = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 125 |
+
generate(model, tokenizer, prompt=formatted, max_tokens=500, sampler=sampler, verbose=True)
|
| 126 |
+
```
|
| 127 |
+
|
| 128 |
+
### GGUF (llama.cpp / Ollama / LM Studio)
|
| 129 |
+
```bash
|
| 130 |
+
# Ollama
|
| 131 |
+
ollama run ravenx-cyberagent-v6.2
|
| 132 |
+
|
| 133 |
+
# llama.cpp
|
| 134 |
+
./llama-cli -m RavenX-CyberAgent-v6.2-Q4_K_M.gguf -p "Pentest target.com"
|
| 135 |
+
```
|
| 136 |
+
|
| 137 |
+
## Example Output
|
| 138 |
+
|
| 139 |
+
**Prompt:** "Port 8443 running Apache Tomcat 9.0.31. What do you do?"
|
| 140 |
+
|
| 141 |
+
**Response:**
|
| 142 |
+
```
|
| 143 |
+
Tomcat 9.0.31 on 8443 narrows it down. Critical path:
|
| 144 |
+
|
| 145 |
+
1. Ghostcat (CVE-2020-1938) — AJP connector on 8009
|
| 146 |
+
2. Default credentials: tomcat:tomcat → /manager/html
|
| 147 |
+
3. Browser via MCP if UI is responsive
|
| 148 |
+
4. NIST vulnerability check on 9.0.31
|
| 149 |
+
|
| 150 |
+
<tool_call>
|
| 151 |
+
{"name": "execute_command", "arguments": {"command": "nmap -sV -p 8009,8080,8443 target.com"}}
|
| 152 |
+
</tool_call>
|
| 153 |
+
|
| 154 |
+
<tool_call>
|
| 155 |
+
{"name": "execute_command", "arguments": {"command": "curl -u tomcat:tomcat http://target.com:8080/manager/html"}}
|
| 156 |
+
</tool_call>
|
| 157 |
+
```
|
| 158 |
+
|
| 159 |
+
No repetition. No loops. Direct CVE identification. Immediate execution plan.
|
| 160 |
+
|
| 161 |
+
## Model Details
|
| 162 |
+
|
| 163 |
+
| Spec | Value |
|
| 164 |
+
|------|-------|
|
| 165 |
+
| Base Model | Qwen3.6-35B-A3B (MoE) |
|
| 166 |
+
| Architecture | 35B parameters, Mixture of Experts |
|
| 167 |
+
| Training | LoRA, single pass, Apple Silicon (M4 Max 128GB) |
|
| 168 |
+
| Training Examples | 722,352 security + identity examples |
|
| 169 |
+
| Val Loss | 0.193 |
|
| 170 |
+
| Quantization | MLX (native) / GGUF Q4_K_M (20.7GB) |
|
| 171 |
+
| Context | 512 tokens (training), 32K (inference) |
|
| 172 |
+
| License | Apache 2.0 |
|
| 173 |
+
|
| 174 |
+
## Comparison: v5.1 → v6.2
|
| 175 |
+
|
| 176 |
+
| Metric | v5.1 | v6.2 |
|
| 177 |
+
|--------|------|------|
|
| 178 |
+
| Rounds | 12 | 1 |
|
| 179 |
+
| Val Loss | 0.688 | 0.193 |
|
| 180 |
+
| Repetition | Severe | None |
|
| 181 |
+
| Tool Execution | Guides only | 13 tool_calls direct |
|
| 182 |
+
| RATH Format | None | Full (CVSS + CWE + MITRE) |
|
| 183 |
+
| Reasoning | Overthinking loops | Direct execution |
|
| 184 |
+
|
| 185 |
+
## Built By
|
| 186 |
+
|
| 187 |
+
**Gabriel Garcia** / **RavenX LLC**
|
| 188 |
+
|
| 189 |
+
- 8+ years Apple InfoSec
|
| 190 |
+
- Google AI Professional Certificate
|
| 191 |
+
- Security+, ITIL v3 Foundation
|
| 192 |
+
|
| 193 |
+
Training methodology improvements are ongoing.
|
| 194 |
+
|
| 195 |
+
---
|
| 196 |
+
|
| 197 |
+
> *"We don't attack the firewall. We find the person holding the door open."* — RavenX-CyberAgent
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- set num_sys = 0 %}
|
| 46 |
+
{%- set merged_system = '' %}
|
| 47 |
+
{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
|
| 48 |
+
{%- set first = render_content(messages[0].content, false, true)|trim %}
|
| 49 |
+
{%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
|
| 50 |
+
{%- set second = render_content(messages[1].content, false, true)|trim %}
|
| 51 |
+
{%- set merged_system = first + '\n' + second %}
|
| 52 |
+
{%- set num_sys = 2 %}
|
| 53 |
+
{%- else %}
|
| 54 |
+
{%- set merged_system = first %}
|
| 55 |
+
{%- set num_sys = 1 %}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 59 |
+
{{- '<|im_start|>system\n' }}
|
| 60 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 61 |
+
{%- for tool in tools %}
|
| 62 |
+
{{- "\n" }}
|
| 63 |
+
{{- tool | tojson }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{{- "\n</tools>" }}
|
| 66 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 67 |
+
{%- if merged_system %}
|
| 68 |
+
{{- '\n\n' + merged_system }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{{- '<|im_end|>\n' }}
|
| 71 |
+
{%- else %}
|
| 72 |
+
{%- if merged_system %}
|
| 73 |
+
{{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 77 |
+
{%- for message in messages[::-1] %}
|
| 78 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 79 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 80 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 81 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 82 |
+
{%- set ns.multi_step_tool = false %}
|
| 83 |
+
{%- set ns.last_query_index = index %}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{%- endfor %}
|
| 87 |
+
{%- for message in messages %}
|
| 88 |
+
{%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
|
| 89 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 90 |
+
{%- if message.role == "user" %}
|
| 91 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 92 |
+
{%- elif message.role == "assistant" %}
|
| 93 |
+
{%- set reasoning_content = '' %}
|
| 94 |
+
{%- if message.reasoning_content is string %}
|
| 95 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 96 |
+
{%- else %}
|
| 97 |
+
{%- if '</think>' in content %}
|
| 98 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 99 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 100 |
+
{%- endif %}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 103 |
+
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
|
| 104 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 105 |
+
{%- else %}
|
| 106 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 107 |
+
{%- endif %}
|
| 108 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 109 |
+
{%- for tool_call in message.tool_calls %}
|
| 110 |
+
{%- if tool_call.function is defined %}
|
| 111 |
+
{%- set tool_call = tool_call.function %}
|
| 112 |
+
{%- endif %}
|
| 113 |
+
{%- if loop.first %}
|
| 114 |
+
{%- if content|trim %}
|
| 115 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- else %}
|
| 120 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 121 |
+
{%- endif %}
|
| 122 |
+
{%- if tool_call.arguments is mapping %}
|
| 123 |
+
{%- for args_name in tool_call.arguments %}
|
| 124 |
+
{%- set args_value = tool_call.arguments[args_name] %}
|
| 125 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 126 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 127 |
+
{{- args_value }}
|
| 128 |
+
{{- '\n</parameter>\n' }}
|
| 129 |
+
{%- endfor %}
|
| 130 |
+
{%- endif %}
|
| 131 |
+
{{- '</function>\n</tool_call>' }}
|
| 132 |
+
{%- endfor %}
|
| 133 |
+
{%- endif %}
|
| 134 |
+
{{- '<|im_end|>\n' }}
|
| 135 |
+
{%- elif message.role == "tool" %}
|
| 136 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 137 |
+
{{- '<|im_start|>user' }}
|
| 138 |
+
{%- endif %}
|
| 139 |
+
{{- '\n<tool_response>\n' }}
|
| 140 |
+
{{- content }}
|
| 141 |
+
{{- '\n</tool_response>' }}
|
| 142 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 143 |
+
{{- '<|im_end|>\n' }}
|
| 144 |
+
{%- elif loop.last %}
|
| 145 |
+
{{- '<|im_end|>\n' }}
|
| 146 |
+
{%- endif %}
|
| 147 |
+
{%- endif %}
|
| 148 |
+
{%- endif %}
|
| 149 |
+
{%- endfor %}
|
| 150 |
+
{%- if add_generation_prompt %}
|
| 151 |
+
{{- '<|im_start|>assistant\n' }}
|
| 152 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 153 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 154 |
+
{%- else %}
|
| 155 |
+
{{- '<think>\n' }}
|
| 156 |
+
{%- endif %}
|
| 157 |
+
{%- endif %}
|
| 158 |
+
{#- Unsloth fixes - developer role, tool calling #}
|
config.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"image_token_id": 248056,
|
| 8 |
+
"model_name": "unsloth/Qwen3.6-35B-A3B",
|
| 9 |
+
"model_type": "qwen3_5_moe",
|
| 10 |
+
"pad_token_id": 248055,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": 248044,
|
| 16 |
+
"torch_dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 2048,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"layer_types": [
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"full_attention"
|
| 64 |
+
],
|
| 65 |
+
"linear_conv_kernel_dim": 4,
|
| 66 |
+
"linear_key_head_dim": 128,
|
| 67 |
+
"linear_num_key_heads": 16,
|
| 68 |
+
"linear_num_value_heads": 32,
|
| 69 |
+
"linear_value_head_dim": 128,
|
| 70 |
+
"mamba_ssm_dtype": "float32",
|
| 71 |
+
"max_position_embeddings": 262144,
|
| 72 |
+
"model_type": "qwen3_5_moe_text",
|
| 73 |
+
"moe_intermediate_size": 512,
|
| 74 |
+
"mtp_num_hidden_layers": 1,
|
| 75 |
+
"mtp_use_dedicated_embeddings": false,
|
| 76 |
+
"num_attention_heads": 16,
|
| 77 |
+
"num_experts": 256,
|
| 78 |
+
"num_experts_per_tok": 8,
|
| 79 |
+
"num_hidden_layers": 40,
|
| 80 |
+
"num_key_value_heads": 2,
|
| 81 |
+
"output_router_logits": false,
|
| 82 |
+
"pad_token_id": null,
|
| 83 |
+
"partial_rotary_factor": 0.25,
|
| 84 |
+
"rms_norm_eps": 1e-06,
|
| 85 |
+
"rope_parameters": {
|
| 86 |
+
"mrope_interleaved": true,
|
| 87 |
+
"mrope_section": [
|
| 88 |
+
11,
|
| 89 |
+
11,
|
| 90 |
+
10
|
| 91 |
+
],
|
| 92 |
+
"partial_rotary_factor": 0.25,
|
| 93 |
+
"rope_theta": 10000000,
|
| 94 |
+
"type": "default"
|
| 95 |
+
},
|
| 96 |
+
"router_aux_loss_coef": 0.001,
|
| 97 |
+
"shared_expert_intermediate_size": 512,
|
| 98 |
+
"tie_word_embeddings": false,
|
| 99 |
+
"use_cache": true,
|
| 100 |
+
"vocab_size": 248320
|
| 101 |
+
},
|
| 102 |
+
"tie_word_embeddings": false,
|
| 103 |
+
"torch_dtype": "bfloat16",
|
| 104 |
+
"unsloth_version": "2026.4.1",
|
| 105 |
+
"use_cache": false,
|
| 106 |
+
"video_token_id": 248057,
|
| 107 |
+
"vision_end_token_id": 248054,
|
| 108 |
+
"vision_start_token_id": 248053
|
| 109 |
+
}
|
model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71b9f0d338d725847097f8247e70743483bfc83edc34a52123d01bafeaf75193
|
| 3 |
+
size 4993294233
|
model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bafc694705218365eafe280e628db4d8ebe24cccfbe84af3519a2242088f39ef
|
| 3 |
+
size 5043303270
|
model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54509b8f3e0df383cefd72503f4addd8bd638b7027f12a0b9ac6e2ecd92ec0ad
|
| 3 |
+
size 5043303232
|
model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bc6f749be68e780a1a3743e48fa4d7c45f78a77e8081c580bc4b0a1752e061f
|
| 3 |
+
size 5043303287
|
model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:053ffc6babf1178913352d6b312e7e3f44092947fb15c1383267fb2d2f7ccea7
|
| 3 |
+
size 5056213626
|
model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94f8028122f00a4d2ffcdd5ce2461256a281c601acd18c8aa7386a88b4954ded
|
| 3 |
+
size 5043303282
|
model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a5357b010ff1e1417c64a8d38edcd4ee119dae3cfa486c5896bd3c44718dbf6
|
| 3 |
+
size 5043303272
|
model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7294e60bf024a7d2bd3c360c8302cd32af5fb032f2cca744dbedf3080b9a3f
|
| 3 |
+
size 5043303316
|
model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1a9f5bdb9a30a250eea9c32c4f95b86c2a05ddf984aabf699bb57d60fdcb77a
|
| 3 |
+
size 5056213610
|
model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cc458c15b0fb638d6b812edf0249fe6f658f27bdcabd1ff2df764debab2e063
|
| 3 |
+
size 5043303296
|
model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:418a0efc9fd0f786e839381848d25a247ecbc88a0f35218c9122d0c99b608fdf
|
| 3 |
+
size 5043303306
|
model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60d10c422e985cbc0ec3e5fb9d3e16912a533802d2dda398728eaf3d2788732c
|
| 3 |
+
size 5043303276
|
model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f431a0cd5be26375d7b9d8a14cef46bde5f478c425ee00aa99f690c9e919ef71
|
| 3 |
+
size 5056213678
|
model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ceb7889b4044afdb343e4e3423fbb2ff1396b6021285d58f555b10045cbf706f
|
| 3 |
+
size 3769655485
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,741 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 69321221376,
|
| 4 |
+
"total_parameters": 34660608768
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.lm_head.weight": "model-00014-of-00014.safetensors",
|
| 8 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 10 |
+
"language_model.model.layers.0.linear_attn.A_log": "model-00001-of-00014.safetensors",
|
| 11 |
+
"language_model.model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00014.safetensors",
|
| 12 |
+
"language_model.model.layers.0.linear_attn.dt_bias": "model-00001-of-00014.safetensors",
|
| 13 |
+
"language_model.model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00014.safetensors",
|
| 14 |
+
"language_model.model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00014.safetensors",
|
| 15 |
+
"language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00014.safetensors",
|
| 16 |
+
"language_model.model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00014.safetensors",
|
| 17 |
+
"language_model.model.layers.0.linear_attn.norm.weight": "model-00001-of-00014.safetensors",
|
| 18 |
+
"language_model.model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00014.safetensors",
|
| 19 |
+
"language_model.model.layers.0.mlp.gate.weight": "model-00001-of-00014.safetensors",
|
| 20 |
+
"language_model.model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 21 |
+
"language_model.model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 22 |
+
"language_model.model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 23 |
+
"language_model.model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00014.safetensors",
|
| 24 |
+
"language_model.model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 25 |
+
"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 26 |
+
"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 27 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 28 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 29 |
+
"language_model.model.layers.1.linear_attn.A_log": "model-00001-of-00014.safetensors",
|
| 30 |
+
"language_model.model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00014.safetensors",
|
| 31 |
+
"language_model.model.layers.1.linear_attn.dt_bias": "model-00001-of-00014.safetensors",
|
| 32 |
+
"language_model.model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00014.safetensors",
|
| 33 |
+
"language_model.model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00014.safetensors",
|
| 34 |
+
"language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00014.safetensors",
|
| 35 |
+
"language_model.model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00014.safetensors",
|
| 36 |
+
"language_model.model.layers.1.linear_attn.norm.weight": "model-00001-of-00014.safetensors",
|
| 37 |
+
"language_model.model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00014.safetensors",
|
| 38 |
+
"language_model.model.layers.1.mlp.gate.weight": "model-00001-of-00014.safetensors",
|
| 39 |
+
"language_model.model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 40 |
+
"language_model.model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 41 |
+
"language_model.model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 42 |
+
"language_model.model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00014.safetensors",
|
| 43 |
+
"language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 44 |
+
"language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 45 |
+
"language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 46 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 47 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 48 |
+
"language_model.model.layers.10.linear_attn.A_log": "model-00004-of-00014.safetensors",
|
| 49 |
+
"language_model.model.layers.10.linear_attn.conv1d.weight": "model-00004-of-00014.safetensors",
|
| 50 |
+
"language_model.model.layers.10.linear_attn.dt_bias": "model-00004-of-00014.safetensors",
|
| 51 |
+
"language_model.model.layers.10.linear_attn.in_proj_a.weight": "model-00004-of-00014.safetensors",
|
| 52 |
+
"language_model.model.layers.10.linear_attn.in_proj_b.weight": "model-00004-of-00014.safetensors",
|
| 53 |
+
"language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model-00004-of-00014.safetensors",
|
| 54 |
+
"language_model.model.layers.10.linear_attn.in_proj_z.weight": "model-00004-of-00014.safetensors",
|
| 55 |
+
"language_model.model.layers.10.linear_attn.norm.weight": "model-00004-of-00014.safetensors",
|
| 56 |
+
"language_model.model.layers.10.linear_attn.out_proj.weight": "model-00004-of-00014.safetensors",
|
| 57 |
+
"language_model.model.layers.10.mlp.gate.weight": "model-00004-of-00014.safetensors",
|
| 58 |
+
"language_model.model.layers.10.mlp.shared_expert.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 59 |
+
"language_model.model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 60 |
+
"language_model.model.layers.10.mlp.shared_expert.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 61 |
+
"language_model.model.layers.10.mlp.shared_expert_gate.weight": "model-00004-of-00014.safetensors",
|
| 62 |
+
"language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 63 |
+
"language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 64 |
+
"language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 65 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 66 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 67 |
+
"language_model.model.layers.11.mlp.gate.weight": "model-00004-of-00014.safetensors",
|
| 68 |
+
"language_model.model.layers.11.mlp.shared_expert.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 69 |
+
"language_model.model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 70 |
+
"language_model.model.layers.11.mlp.shared_expert.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 71 |
+
"language_model.model.layers.11.mlp.shared_expert_gate.weight": "model-00005-of-00014.safetensors",
|
| 72 |
+
"language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 73 |
+
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 74 |
+
"language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 75 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 76 |
+
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 77 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 78 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 79 |
+
"language_model.model.layers.11.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 80 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 81 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 82 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 83 |
+
"language_model.model.layers.12.linear_attn.A_log": "model-00005-of-00014.safetensors",
|
| 84 |
+
"language_model.model.layers.12.linear_attn.conv1d.weight": "model-00005-of-00014.safetensors",
|
| 85 |
+
"language_model.model.layers.12.linear_attn.dt_bias": "model-00005-of-00014.safetensors",
|
| 86 |
+
"language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00005-of-00014.safetensors",
|
| 87 |
+
"language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00005-of-00014.safetensors",
|
| 88 |
+
"language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00005-of-00014.safetensors",
|
| 89 |
+
"language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00005-of-00014.safetensors",
|
| 90 |
+
"language_model.model.layers.12.linear_attn.norm.weight": "model-00005-of-00014.safetensors",
|
| 91 |
+
"language_model.model.layers.12.linear_attn.out_proj.weight": "model-00005-of-00014.safetensors",
|
| 92 |
+
"language_model.model.layers.12.mlp.gate.weight": "model-00005-of-00014.safetensors",
|
| 93 |
+
"language_model.model.layers.12.mlp.shared_expert.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 94 |
+
"language_model.model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 95 |
+
"language_model.model.layers.12.mlp.shared_expert.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 96 |
+
"language_model.model.layers.12.mlp.shared_expert_gate.weight": "model-00005-of-00014.safetensors",
|
| 97 |
+
"language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 98 |
+
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 99 |
+
"language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 100 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 101 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 102 |
+
"language_model.model.layers.13.linear_attn.A_log": "model-00005-of-00014.safetensors",
|
| 103 |
+
"language_model.model.layers.13.linear_attn.conv1d.weight": "model-00005-of-00014.safetensors",
|
| 104 |
+
"language_model.model.layers.13.linear_attn.dt_bias": "model-00005-of-00014.safetensors",
|
| 105 |
+
"language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00005-of-00014.safetensors",
|
| 106 |
+
"language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00005-of-00014.safetensors",
|
| 107 |
+
"language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00005-of-00014.safetensors",
|
| 108 |
+
"language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00005-of-00014.safetensors",
|
| 109 |
+
"language_model.model.layers.13.linear_attn.norm.weight": "model-00005-of-00014.safetensors",
|
| 110 |
+
"language_model.model.layers.13.linear_attn.out_proj.weight": "model-00005-of-00014.safetensors",
|
| 111 |
+
"language_model.model.layers.13.mlp.gate.weight": "model-00005-of-00014.safetensors",
|
| 112 |
+
"language_model.model.layers.13.mlp.shared_expert.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 113 |
+
"language_model.model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 114 |
+
"language_model.model.layers.13.mlp.shared_expert.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 115 |
+
"language_model.model.layers.13.mlp.shared_expert_gate.weight": "model-00005-of-00014.safetensors",
|
| 116 |
+
"language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 117 |
+
"language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 118 |
+
"language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 119 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 120 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 121 |
+
"language_model.model.layers.14.linear_attn.A_log": "model-00005-of-00014.safetensors",
|
| 122 |
+
"language_model.model.layers.14.linear_attn.conv1d.weight": "model-00005-of-00014.safetensors",
|
| 123 |
+
"language_model.model.layers.14.linear_attn.dt_bias": "model-00005-of-00014.safetensors",
|
| 124 |
+
"language_model.model.layers.14.linear_attn.in_proj_a.weight": "model-00005-of-00014.safetensors",
|
| 125 |
+
"language_model.model.layers.14.linear_attn.in_proj_b.weight": "model-00005-of-00014.safetensors",
|
| 126 |
+
"language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model-00005-of-00014.safetensors",
|
| 127 |
+
"language_model.model.layers.14.linear_attn.in_proj_z.weight": "model-00005-of-00014.safetensors",
|
| 128 |
+
"language_model.model.layers.14.linear_attn.norm.weight": "model-00005-of-00014.safetensors",
|
| 129 |
+
"language_model.model.layers.14.linear_attn.out_proj.weight": "model-00005-of-00014.safetensors",
|
| 130 |
+
"language_model.model.layers.14.mlp.gate.weight": "model-00005-of-00014.safetensors",
|
| 131 |
+
"language_model.model.layers.14.mlp.shared_expert.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 132 |
+
"language_model.model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 133 |
+
"language_model.model.layers.14.mlp.shared_expert.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 134 |
+
"language_model.model.layers.14.mlp.shared_expert_gate.weight": "model-00006-of-00014.safetensors",
|
| 135 |
+
"language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 136 |
+
"language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 137 |
+
"language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 138 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 139 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 140 |
+
"language_model.model.layers.15.mlp.gate.weight": "model-00006-of-00014.safetensors",
|
| 141 |
+
"language_model.model.layers.15.mlp.shared_expert.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 142 |
+
"language_model.model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 143 |
+
"language_model.model.layers.15.mlp.shared_expert.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 144 |
+
"language_model.model.layers.15.mlp.shared_expert_gate.weight": "model-00006-of-00014.safetensors",
|
| 145 |
+
"language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 146 |
+
"language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 147 |
+
"language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 148 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 149 |
+
"language_model.model.layers.15.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 150 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 151 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 152 |
+
"language_model.model.layers.15.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 153 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 154 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 155 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 156 |
+
"language_model.model.layers.16.linear_attn.A_log": "model-00006-of-00014.safetensors",
|
| 157 |
+
"language_model.model.layers.16.linear_attn.conv1d.weight": "model-00006-of-00014.safetensors",
|
| 158 |
+
"language_model.model.layers.16.linear_attn.dt_bias": "model-00006-of-00014.safetensors",
|
| 159 |
+
"language_model.model.layers.16.linear_attn.in_proj_a.weight": "model-00006-of-00014.safetensors",
|
| 160 |
+
"language_model.model.layers.16.linear_attn.in_proj_b.weight": "model-00006-of-00014.safetensors",
|
| 161 |
+
"language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model-00006-of-00014.safetensors",
|
| 162 |
+
"language_model.model.layers.16.linear_attn.in_proj_z.weight": "model-00006-of-00014.safetensors",
|
| 163 |
+
"language_model.model.layers.16.linear_attn.norm.weight": "model-00006-of-00014.safetensors",
|
| 164 |
+
"language_model.model.layers.16.linear_attn.out_proj.weight": "model-00006-of-00014.safetensors",
|
| 165 |
+
"language_model.model.layers.16.mlp.gate.weight": "model-00006-of-00014.safetensors",
|
| 166 |
+
"language_model.model.layers.16.mlp.shared_expert.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 167 |
+
"language_model.model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 168 |
+
"language_model.model.layers.16.mlp.shared_expert.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 169 |
+
"language_model.model.layers.16.mlp.shared_expert_gate.weight": "model-00006-of-00014.safetensors",
|
| 170 |
+
"language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 171 |
+
"language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 172 |
+
"language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 173 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 174 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 175 |
+
"language_model.model.layers.17.linear_attn.A_log": "model-00006-of-00014.safetensors",
|
| 176 |
+
"language_model.model.layers.17.linear_attn.conv1d.weight": "model-00006-of-00014.safetensors",
|
| 177 |
+
"language_model.model.layers.17.linear_attn.dt_bias": "model-00006-of-00014.safetensors",
|
| 178 |
+
"language_model.model.layers.17.linear_attn.in_proj_a.weight": "model-00006-of-00014.safetensors",
|
| 179 |
+
"language_model.model.layers.17.linear_attn.in_proj_b.weight": "model-00006-of-00014.safetensors",
|
| 180 |
+
"language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model-00006-of-00014.safetensors",
|
| 181 |
+
"language_model.model.layers.17.linear_attn.in_proj_z.weight": "model-00006-of-00014.safetensors",
|
| 182 |
+
"language_model.model.layers.17.linear_attn.norm.weight": "model-00006-of-00014.safetensors",
|
| 183 |
+
"language_model.model.layers.17.linear_attn.out_proj.weight": "model-00006-of-00014.safetensors",
|
| 184 |
+
"language_model.model.layers.17.mlp.gate.weight": "model-00006-of-00014.safetensors",
|
| 185 |
+
"language_model.model.layers.17.mlp.shared_expert.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 186 |
+
"language_model.model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 187 |
+
"language_model.model.layers.17.mlp.shared_expert.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 188 |
+
"language_model.model.layers.17.mlp.shared_expert_gate.weight": "model-00007-of-00014.safetensors",
|
| 189 |
+
"language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 190 |
+
"language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 191 |
+
"language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 192 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 193 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 194 |
+
"language_model.model.layers.18.linear_attn.A_log": "model-00007-of-00014.safetensors",
|
| 195 |
+
"language_model.model.layers.18.linear_attn.conv1d.weight": "model-00007-of-00014.safetensors",
|
| 196 |
+
"language_model.model.layers.18.linear_attn.dt_bias": "model-00007-of-00014.safetensors",
|
| 197 |
+
"language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00007-of-00014.safetensors",
|
| 198 |
+
"language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00007-of-00014.safetensors",
|
| 199 |
+
"language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00007-of-00014.safetensors",
|
| 200 |
+
"language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00007-of-00014.safetensors",
|
| 201 |
+
"language_model.model.layers.18.linear_attn.norm.weight": "model-00007-of-00014.safetensors",
|
| 202 |
+
"language_model.model.layers.18.linear_attn.out_proj.weight": "model-00007-of-00014.safetensors",
|
| 203 |
+
"language_model.model.layers.18.mlp.gate.weight": "model-00007-of-00014.safetensors",
|
| 204 |
+
"language_model.model.layers.18.mlp.shared_expert.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 205 |
+
"language_model.model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 206 |
+
"language_model.model.layers.18.mlp.shared_expert.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 207 |
+
"language_model.model.layers.18.mlp.shared_expert_gate.weight": "model-00007-of-00014.safetensors",
|
| 208 |
+
"language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 209 |
+
"language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 210 |
+
"language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 211 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 212 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 213 |
+
"language_model.model.layers.19.mlp.gate.weight": "model-00007-of-00014.safetensors",
|
| 214 |
+
"language_model.model.layers.19.mlp.shared_expert.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 215 |
+
"language_model.model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 216 |
+
"language_model.model.layers.19.mlp.shared_expert.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 217 |
+
"language_model.model.layers.19.mlp.shared_expert_gate.weight": "model-00007-of-00014.safetensors",
|
| 218 |
+
"language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 219 |
+
"language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 220 |
+
"language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 221 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 222 |
+
"language_model.model.layers.19.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 223 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 224 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 225 |
+
"language_model.model.layers.19.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 226 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 227 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 228 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 229 |
+
"language_model.model.layers.2.linear_attn.A_log": "model-00001-of-00014.safetensors",
|
| 230 |
+
"language_model.model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00014.safetensors",
|
| 231 |
+
"language_model.model.layers.2.linear_attn.dt_bias": "model-00001-of-00014.safetensors",
|
| 232 |
+
"language_model.model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00014.safetensors",
|
| 233 |
+
"language_model.model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00014.safetensors",
|
| 234 |
+
"language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00014.safetensors",
|
| 235 |
+
"language_model.model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00014.safetensors",
|
| 236 |
+
"language_model.model.layers.2.linear_attn.norm.weight": "model-00001-of-00014.safetensors",
|
| 237 |
+
"language_model.model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00014.safetensors",
|
| 238 |
+
"language_model.model.layers.2.mlp.gate.weight": "model-00001-of-00014.safetensors",
|
| 239 |
+
"language_model.model.layers.2.mlp.shared_expert.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 240 |
+
"language_model.model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 241 |
+
"language_model.model.layers.2.mlp.shared_expert.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 242 |
+
"language_model.model.layers.2.mlp.shared_expert_gate.weight": "model-00002-of-00014.safetensors",
|
| 243 |
+
"language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 244 |
+
"language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 245 |
+
"language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 246 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 247 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 248 |
+
"language_model.model.layers.20.linear_attn.A_log": "model-00007-of-00014.safetensors",
|
| 249 |
+
"language_model.model.layers.20.linear_attn.conv1d.weight": "model-00007-of-00014.safetensors",
|
| 250 |
+
"language_model.model.layers.20.linear_attn.dt_bias": "model-00007-of-00014.safetensors",
|
| 251 |
+
"language_model.model.layers.20.linear_attn.in_proj_a.weight": "model-00007-of-00014.safetensors",
|
| 252 |
+
"language_model.model.layers.20.linear_attn.in_proj_b.weight": "model-00007-of-00014.safetensors",
|
| 253 |
+
"language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model-00007-of-00014.safetensors",
|
| 254 |
+
"language_model.model.layers.20.linear_attn.in_proj_z.weight": "model-00007-of-00014.safetensors",
|
| 255 |
+
"language_model.model.layers.20.linear_attn.norm.weight": "model-00007-of-00014.safetensors",
|
| 256 |
+
"language_model.model.layers.20.linear_attn.out_proj.weight": "model-00007-of-00014.safetensors",
|
| 257 |
+
"language_model.model.layers.20.mlp.gate.weight": "model-00007-of-00014.safetensors",
|
| 258 |
+
"language_model.model.layers.20.mlp.shared_expert.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 259 |
+
"language_model.model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 260 |
+
"language_model.model.layers.20.mlp.shared_expert.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 261 |
+
"language_model.model.layers.20.mlp.shared_expert_gate.weight": "model-00008-of-00014.safetensors",
|
| 262 |
+
"language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 263 |
+
"language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 264 |
+
"language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 265 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 266 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 267 |
+
"language_model.model.layers.21.linear_attn.A_log": "model-00008-of-00014.safetensors",
|
| 268 |
+
"language_model.model.layers.21.linear_attn.conv1d.weight": "model-00008-of-00014.safetensors",
|
| 269 |
+
"language_model.model.layers.21.linear_attn.dt_bias": "model-00008-of-00014.safetensors",
|
| 270 |
+
"language_model.model.layers.21.linear_attn.in_proj_a.weight": "model-00008-of-00014.safetensors",
|
| 271 |
+
"language_model.model.layers.21.linear_attn.in_proj_b.weight": "model-00008-of-00014.safetensors",
|
| 272 |
+
"language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model-00008-of-00014.safetensors",
|
| 273 |
+
"language_model.model.layers.21.linear_attn.in_proj_z.weight": "model-00008-of-00014.safetensors",
|
| 274 |
+
"language_model.model.layers.21.linear_attn.norm.weight": "model-00008-of-00014.safetensors",
|
| 275 |
+
"language_model.model.layers.21.linear_attn.out_proj.weight": "model-00008-of-00014.safetensors",
|
| 276 |
+
"language_model.model.layers.21.mlp.gate.weight": "model-00008-of-00014.safetensors",
|
| 277 |
+
"language_model.model.layers.21.mlp.shared_expert.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 278 |
+
"language_model.model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 279 |
+
"language_model.model.layers.21.mlp.shared_expert.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 280 |
+
"language_model.model.layers.21.mlp.shared_expert_gate.weight": "model-00008-of-00014.safetensors",
|
| 281 |
+
"language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 282 |
+
"language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 283 |
+
"language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 284 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 285 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 286 |
+
"language_model.model.layers.22.linear_attn.A_log": "model-00008-of-00014.safetensors",
|
| 287 |
+
"language_model.model.layers.22.linear_attn.conv1d.weight": "model-00008-of-00014.safetensors",
|
| 288 |
+
"language_model.model.layers.22.linear_attn.dt_bias": "model-00008-of-00014.safetensors",
|
| 289 |
+
"language_model.model.layers.22.linear_attn.in_proj_a.weight": "model-00008-of-00014.safetensors",
|
| 290 |
+
"language_model.model.layers.22.linear_attn.in_proj_b.weight": "model-00008-of-00014.safetensors",
|
| 291 |
+
"language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model-00008-of-00014.safetensors",
|
| 292 |
+
"language_model.model.layers.22.linear_attn.in_proj_z.weight": "model-00008-of-00014.safetensors",
|
| 293 |
+
"language_model.model.layers.22.linear_attn.norm.weight": "model-00008-of-00014.safetensors",
|
| 294 |
+
"language_model.model.layers.22.linear_attn.out_proj.weight": "model-00008-of-00014.safetensors",
|
| 295 |
+
"language_model.model.layers.22.mlp.gate.weight": "model-00008-of-00014.safetensors",
|
| 296 |
+
"language_model.model.layers.22.mlp.shared_expert.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 297 |
+
"language_model.model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 298 |
+
"language_model.model.layers.22.mlp.shared_expert.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 299 |
+
"language_model.model.layers.22.mlp.shared_expert_gate.weight": "model-00008-of-00014.safetensors",
|
| 300 |
+
"language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 301 |
+
"language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 302 |
+
"language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 303 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 304 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 305 |
+
"language_model.model.layers.23.mlp.gate.weight": "model-00008-of-00014.safetensors",
|
| 306 |
+
"language_model.model.layers.23.mlp.shared_expert.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 307 |
+
"language_model.model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 308 |
+
"language_model.model.layers.23.mlp.shared_expert.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 309 |
+
"language_model.model.layers.23.mlp.shared_expert_gate.weight": "model-00009-of-00014.safetensors",
|
| 310 |
+
"language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 311 |
+
"language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 312 |
+
"language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 313 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 314 |
+
"language_model.model.layers.23.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 315 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 316 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 317 |
+
"language_model.model.layers.23.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 318 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 319 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 320 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 321 |
+
"language_model.model.layers.24.linear_attn.A_log": "model-00009-of-00014.safetensors",
|
| 322 |
+
"language_model.model.layers.24.linear_attn.conv1d.weight": "model-00009-of-00014.safetensors",
|
| 323 |
+
"language_model.model.layers.24.linear_attn.dt_bias": "model-00009-of-00014.safetensors",
|
| 324 |
+
"language_model.model.layers.24.linear_attn.in_proj_a.weight": "model-00009-of-00014.safetensors",
|
| 325 |
+
"language_model.model.layers.24.linear_attn.in_proj_b.weight": "model-00009-of-00014.safetensors",
|
| 326 |
+
"language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model-00009-of-00014.safetensors",
|
| 327 |
+
"language_model.model.layers.24.linear_attn.in_proj_z.weight": "model-00009-of-00014.safetensors",
|
| 328 |
+
"language_model.model.layers.24.linear_attn.norm.weight": "model-00009-of-00014.safetensors",
|
| 329 |
+
"language_model.model.layers.24.linear_attn.out_proj.weight": "model-00009-of-00014.safetensors",
|
| 330 |
+
"language_model.model.layers.24.mlp.gate.weight": "model-00009-of-00014.safetensors",
|
| 331 |
+
"language_model.model.layers.24.mlp.shared_expert.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 332 |
+
"language_model.model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 333 |
+
"language_model.model.layers.24.mlp.shared_expert.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 334 |
+
"language_model.model.layers.24.mlp.shared_expert_gate.weight": "model-00009-of-00014.safetensors",
|
| 335 |
+
"language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 336 |
+
"language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 337 |
+
"language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 338 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 339 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 340 |
+
"language_model.model.layers.25.linear_attn.A_log": "model-00009-of-00014.safetensors",
|
| 341 |
+
"language_model.model.layers.25.linear_attn.conv1d.weight": "model-00009-of-00014.safetensors",
|
| 342 |
+
"language_model.model.layers.25.linear_attn.dt_bias": "model-00009-of-00014.safetensors",
|
| 343 |
+
"language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00009-of-00014.safetensors",
|
| 344 |
+
"language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00009-of-00014.safetensors",
|
| 345 |
+
"language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00009-of-00014.safetensors",
|
| 346 |
+
"language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00009-of-00014.safetensors",
|
| 347 |
+
"language_model.model.layers.25.linear_attn.norm.weight": "model-00009-of-00014.safetensors",
|
| 348 |
+
"language_model.model.layers.25.linear_attn.out_proj.weight": "model-00009-of-00014.safetensors",
|
| 349 |
+
"language_model.model.layers.25.mlp.gate.weight": "model-00009-of-00014.safetensors",
|
| 350 |
+
"language_model.model.layers.25.mlp.shared_expert.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 351 |
+
"language_model.model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 352 |
+
"language_model.model.layers.25.mlp.shared_expert.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 353 |
+
"language_model.model.layers.25.mlp.shared_expert_gate.weight": "model-00009-of-00014.safetensors",
|
| 354 |
+
"language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 355 |
+
"language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 356 |
+
"language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 357 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 358 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 359 |
+
"language_model.model.layers.26.linear_attn.A_log": "model-00009-of-00014.safetensors",
|
| 360 |
+
"language_model.model.layers.26.linear_attn.conv1d.weight": "model-00009-of-00014.safetensors",
|
| 361 |
+
"language_model.model.layers.26.linear_attn.dt_bias": "model-00009-of-00014.safetensors",
|
| 362 |
+
"language_model.model.layers.26.linear_attn.in_proj_a.weight": "model-00009-of-00014.safetensors",
|
| 363 |
+
"language_model.model.layers.26.linear_attn.in_proj_b.weight": "model-00009-of-00014.safetensors",
|
| 364 |
+
"language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model-00009-of-00014.safetensors",
|
| 365 |
+
"language_model.model.layers.26.linear_attn.in_proj_z.weight": "model-00009-of-00014.safetensors",
|
| 366 |
+
"language_model.model.layers.26.linear_attn.norm.weight": "model-00009-of-00014.safetensors",
|
| 367 |
+
"language_model.model.layers.26.linear_attn.out_proj.weight": "model-00009-of-00014.safetensors",
|
| 368 |
+
"language_model.model.layers.26.mlp.gate.weight": "model-00009-of-00014.safetensors",
|
| 369 |
+
"language_model.model.layers.26.mlp.shared_expert.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 370 |
+
"language_model.model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 371 |
+
"language_model.model.layers.26.mlp.shared_expert.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 372 |
+
"language_model.model.layers.26.mlp.shared_expert_gate.weight": "model-00010-of-00014.safetensors",
|
| 373 |
+
"language_model.model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 374 |
+
"language_model.model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 375 |
+
"language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 376 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 377 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 378 |
+
"language_model.model.layers.27.mlp.gate.weight": "model-00010-of-00014.safetensors",
|
| 379 |
+
"language_model.model.layers.27.mlp.shared_expert.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 380 |
+
"language_model.model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 381 |
+
"language_model.model.layers.27.mlp.shared_expert.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 382 |
+
"language_model.model.layers.27.mlp.shared_expert_gate.weight": "model-00010-of-00014.safetensors",
|
| 383 |
+
"language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 384 |
+
"language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 385 |
+
"language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 386 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 387 |
+
"language_model.model.layers.27.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 388 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 389 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 390 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 391 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 392 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 393 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 394 |
+
"language_model.model.layers.28.linear_attn.A_log": "model-00010-of-00014.safetensors",
|
| 395 |
+
"language_model.model.layers.28.linear_attn.conv1d.weight": "model-00010-of-00014.safetensors",
|
| 396 |
+
"language_model.model.layers.28.linear_attn.dt_bias": "model-00010-of-00014.safetensors",
|
| 397 |
+
"language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00010-of-00014.safetensors",
|
| 398 |
+
"language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00010-of-00014.safetensors",
|
| 399 |
+
"language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00010-of-00014.safetensors",
|
| 400 |
+
"language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00010-of-00014.safetensors",
|
| 401 |
+
"language_model.model.layers.28.linear_attn.norm.weight": "model-00010-of-00014.safetensors",
|
| 402 |
+
"language_model.model.layers.28.linear_attn.out_proj.weight": "model-00010-of-00014.safetensors",
|
| 403 |
+
"language_model.model.layers.28.mlp.gate.weight": "model-00010-of-00014.safetensors",
|
| 404 |
+
"language_model.model.layers.28.mlp.shared_expert.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 405 |
+
"language_model.model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 406 |
+
"language_model.model.layers.28.mlp.shared_expert.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 407 |
+
"language_model.model.layers.28.mlp.shared_expert_gate.weight": "model-00010-of-00014.safetensors",
|
| 408 |
+
"language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 409 |
+
"language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 410 |
+
"language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 411 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 412 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 413 |
+
"language_model.model.layers.29.linear_attn.A_log": "model-00010-of-00014.safetensors",
|
| 414 |
+
"language_model.model.layers.29.linear_attn.conv1d.weight": "model-00010-of-00014.safetensors",
|
| 415 |
+
"language_model.model.layers.29.linear_attn.dt_bias": "model-00010-of-00014.safetensors",
|
| 416 |
+
"language_model.model.layers.29.linear_attn.in_proj_a.weight": "model-00010-of-00014.safetensors",
|
| 417 |
+
"language_model.model.layers.29.linear_attn.in_proj_b.weight": "model-00010-of-00014.safetensors",
|
| 418 |
+
"language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model-00010-of-00014.safetensors",
|
| 419 |
+
"language_model.model.layers.29.linear_attn.in_proj_z.weight": "model-00010-of-00014.safetensors",
|
| 420 |
+
"language_model.model.layers.29.linear_attn.norm.weight": "model-00010-of-00014.safetensors",
|
| 421 |
+
"language_model.model.layers.29.linear_attn.out_proj.weight": "model-00010-of-00014.safetensors",
|
| 422 |
+
"language_model.model.layers.29.mlp.gate.weight": "model-00010-of-00014.safetensors",
|
| 423 |
+
"language_model.model.layers.29.mlp.shared_expert.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 424 |
+
"language_model.model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 425 |
+
"language_model.model.layers.29.mlp.shared_expert.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 426 |
+
"language_model.model.layers.29.mlp.shared_expert_gate.weight": "model-00011-of-00014.safetensors",
|
| 427 |
+
"language_model.model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 428 |
+
"language_model.model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 429 |
+
"language_model.model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 430 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 431 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 432 |
+
"language_model.model.layers.3.mlp.gate.weight": "model-00002-of-00014.safetensors",
|
| 433 |
+
"language_model.model.layers.3.mlp.shared_expert.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 434 |
+
"language_model.model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 435 |
+
"language_model.model.layers.3.mlp.shared_expert.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 436 |
+
"language_model.model.layers.3.mlp.shared_expert_gate.weight": "model-00002-of-00014.safetensors",
|
| 437 |
+
"language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 438 |
+
"language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 439 |
+
"language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 440 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 441 |
+
"language_model.model.layers.3.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 442 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 443 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 444 |
+
"language_model.model.layers.3.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 445 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 446 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 447 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 448 |
+
"language_model.model.layers.30.linear_attn.A_log": "model-00011-of-00014.safetensors",
|
| 449 |
+
"language_model.model.layers.30.linear_attn.conv1d.weight": "model-00011-of-00014.safetensors",
|
| 450 |
+
"language_model.model.layers.30.linear_attn.dt_bias": "model-00011-of-00014.safetensors",
|
| 451 |
+
"language_model.model.layers.30.linear_attn.in_proj_a.weight": "model-00011-of-00014.safetensors",
|
| 452 |
+
"language_model.model.layers.30.linear_attn.in_proj_b.weight": "model-00011-of-00014.safetensors",
|
| 453 |
+
"language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model-00011-of-00014.safetensors",
|
| 454 |
+
"language_model.model.layers.30.linear_attn.in_proj_z.weight": "model-00011-of-00014.safetensors",
|
| 455 |
+
"language_model.model.layers.30.linear_attn.norm.weight": "model-00011-of-00014.safetensors",
|
| 456 |
+
"language_model.model.layers.30.linear_attn.out_proj.weight": "model-00011-of-00014.safetensors",
|
| 457 |
+
"language_model.model.layers.30.mlp.gate.weight": "model-00011-of-00014.safetensors",
|
| 458 |
+
"language_model.model.layers.30.mlp.shared_expert.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 459 |
+
"language_model.model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 460 |
+
"language_model.model.layers.30.mlp.shared_expert.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 461 |
+
"language_model.model.layers.30.mlp.shared_expert_gate.weight": "model-00011-of-00014.safetensors",
|
| 462 |
+
"language_model.model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 463 |
+
"language_model.model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 464 |
+
"language_model.model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 465 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 466 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 467 |
+
"language_model.model.layers.31.mlp.gate.weight": "model-00011-of-00014.safetensors",
|
| 468 |
+
"language_model.model.layers.31.mlp.shared_expert.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 469 |
+
"language_model.model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 470 |
+
"language_model.model.layers.31.mlp.shared_expert.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 471 |
+
"language_model.model.layers.31.mlp.shared_expert_gate.weight": "model-00011-of-00014.safetensors",
|
| 472 |
+
"language_model.model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 473 |
+
"language_model.model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 474 |
+
"language_model.model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 475 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 476 |
+
"language_model.model.layers.31.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 477 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 478 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 479 |
+
"language_model.model.layers.31.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 480 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 481 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 482 |
+
"language_model.model.layers.32.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 483 |
+
"language_model.model.layers.32.linear_attn.A_log": "model-00011-of-00014.safetensors",
|
| 484 |
+
"language_model.model.layers.32.linear_attn.conv1d.weight": "model-00011-of-00014.safetensors",
|
| 485 |
+
"language_model.model.layers.32.linear_attn.dt_bias": "model-00011-of-00014.safetensors",
|
| 486 |
+
"language_model.model.layers.32.linear_attn.in_proj_a.weight": "model-00011-of-00014.safetensors",
|
| 487 |
+
"language_model.model.layers.32.linear_attn.in_proj_b.weight": "model-00011-of-00014.safetensors",
|
| 488 |
+
"language_model.model.layers.32.linear_attn.in_proj_qkv.weight": "model-00011-of-00014.safetensors",
|
| 489 |
+
"language_model.model.layers.32.linear_attn.in_proj_z.weight": "model-00011-of-00014.safetensors",
|
| 490 |
+
"language_model.model.layers.32.linear_attn.norm.weight": "model-00011-of-00014.safetensors",
|
| 491 |
+
"language_model.model.layers.32.linear_attn.out_proj.weight": "model-00011-of-00014.safetensors",
|
| 492 |
+
"language_model.model.layers.32.mlp.gate.weight": "model-00011-of-00014.safetensors",
|
| 493 |
+
"language_model.model.layers.32.mlp.shared_expert.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 494 |
+
"language_model.model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 495 |
+
"language_model.model.layers.32.mlp.shared_expert.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 496 |
+
"language_model.model.layers.32.mlp.shared_expert_gate.weight": "model-00012-of-00014.safetensors",
|
| 497 |
+
"language_model.model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 498 |
+
"language_model.model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 499 |
+
"language_model.model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 500 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 501 |
+
"language_model.model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 502 |
+
"language_model.model.layers.33.linear_attn.A_log": "model-00012-of-00014.safetensors",
|
| 503 |
+
"language_model.model.layers.33.linear_attn.conv1d.weight": "model-00012-of-00014.safetensors",
|
| 504 |
+
"language_model.model.layers.33.linear_attn.dt_bias": "model-00012-of-00014.safetensors",
|
| 505 |
+
"language_model.model.layers.33.linear_attn.in_proj_a.weight": "model-00012-of-00014.safetensors",
|
| 506 |
+
"language_model.model.layers.33.linear_attn.in_proj_b.weight": "model-00012-of-00014.safetensors",
|
| 507 |
+
"language_model.model.layers.33.linear_attn.in_proj_qkv.weight": "model-00012-of-00014.safetensors",
|
| 508 |
+
"language_model.model.layers.33.linear_attn.in_proj_z.weight": "model-00012-of-00014.safetensors",
|
| 509 |
+
"language_model.model.layers.33.linear_attn.norm.weight": "model-00012-of-00014.safetensors",
|
| 510 |
+
"language_model.model.layers.33.linear_attn.out_proj.weight": "model-00012-of-00014.safetensors",
|
| 511 |
+
"language_model.model.layers.33.mlp.gate.weight": "model-00012-of-00014.safetensors",
|
| 512 |
+
"language_model.model.layers.33.mlp.shared_expert.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 513 |
+
"language_model.model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 514 |
+
"language_model.model.layers.33.mlp.shared_expert.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 515 |
+
"language_model.model.layers.33.mlp.shared_expert_gate.weight": "model-00012-of-00014.safetensors",
|
| 516 |
+
"language_model.model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 517 |
+
"language_model.model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 518 |
+
"language_model.model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 519 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 520 |
+
"language_model.model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 521 |
+
"language_model.model.layers.34.linear_attn.A_log": "model-00012-of-00014.safetensors",
|
| 522 |
+
"language_model.model.layers.34.linear_attn.conv1d.weight": "model-00012-of-00014.safetensors",
|
| 523 |
+
"language_model.model.layers.34.linear_attn.dt_bias": "model-00012-of-00014.safetensors",
|
| 524 |
+
"language_model.model.layers.34.linear_attn.in_proj_a.weight": "model-00012-of-00014.safetensors",
|
| 525 |
+
"language_model.model.layers.34.linear_attn.in_proj_b.weight": "model-00012-of-00014.safetensors",
|
| 526 |
+
"language_model.model.layers.34.linear_attn.in_proj_qkv.weight": "model-00012-of-00014.safetensors",
|
| 527 |
+
"language_model.model.layers.34.linear_attn.in_proj_z.weight": "model-00012-of-00014.safetensors",
|
| 528 |
+
"language_model.model.layers.34.linear_attn.norm.weight": "model-00012-of-00014.safetensors",
|
| 529 |
+
"language_model.model.layers.34.linear_attn.out_proj.weight": "model-00012-of-00014.safetensors",
|
| 530 |
+
"language_model.model.layers.34.mlp.gate.weight": "model-00012-of-00014.safetensors",
|
| 531 |
+
"language_model.model.layers.34.mlp.shared_expert.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 532 |
+
"language_model.model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 533 |
+
"language_model.model.layers.34.mlp.shared_expert.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 534 |
+
"language_model.model.layers.34.mlp.shared_expert_gate.weight": "model-00012-of-00014.safetensors",
|
| 535 |
+
"language_model.model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 536 |
+
"language_model.model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 537 |
+
"language_model.model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 538 |
+
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 539 |
+
"language_model.model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 540 |
+
"language_model.model.layers.35.mlp.gate.weight": "model-00012-of-00014.safetensors",
|
| 541 |
+
"language_model.model.layers.35.mlp.shared_expert.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 542 |
+
"language_model.model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 543 |
+
"language_model.model.layers.35.mlp.shared_expert.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 544 |
+
"language_model.model.layers.35.mlp.shared_expert_gate.weight": "model-00013-of-00014.safetensors",
|
| 545 |
+
"language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 546 |
+
"language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 547 |
+
"language_model.model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 548 |
+
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 549 |
+
"language_model.model.layers.35.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 550 |
+
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 551 |
+
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 552 |
+
"language_model.model.layers.35.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 553 |
+
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 554 |
+
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 555 |
+
"language_model.model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 556 |
+
"language_model.model.layers.36.linear_attn.A_log": "model-00013-of-00014.safetensors",
|
| 557 |
+
"language_model.model.layers.36.linear_attn.conv1d.weight": "model-00013-of-00014.safetensors",
|
| 558 |
+
"language_model.model.layers.36.linear_attn.dt_bias": "model-00013-of-00014.safetensors",
|
| 559 |
+
"language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00013-of-00014.safetensors",
|
| 560 |
+
"language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00013-of-00014.safetensors",
|
| 561 |
+
"language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00013-of-00014.safetensors",
|
| 562 |
+
"language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00013-of-00014.safetensors",
|
| 563 |
+
"language_model.model.layers.36.linear_attn.norm.weight": "model-00013-of-00014.safetensors",
|
| 564 |
+
"language_model.model.layers.36.linear_attn.out_proj.weight": "model-00013-of-00014.safetensors",
|
| 565 |
+
"language_model.model.layers.36.mlp.gate.weight": "model-00013-of-00014.safetensors",
|
| 566 |
+
"language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 567 |
+
"language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 568 |
+
"language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 569 |
+
"language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00013-of-00014.safetensors",
|
| 570 |
+
"language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 571 |
+
"language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 572 |
+
"language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 573 |
+
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 574 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 575 |
+
"language_model.model.layers.37.linear_attn.A_log": "model-00013-of-00014.safetensors",
|
| 576 |
+
"language_model.model.layers.37.linear_attn.conv1d.weight": "model-00013-of-00014.safetensors",
|
| 577 |
+
"language_model.model.layers.37.linear_attn.dt_bias": "model-00013-of-00014.safetensors",
|
| 578 |
+
"language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-00013-of-00014.safetensors",
|
| 579 |
+
"language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-00013-of-00014.safetensors",
|
| 580 |
+
"language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-00013-of-00014.safetensors",
|
| 581 |
+
"language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-00013-of-00014.safetensors",
|
| 582 |
+
"language_model.model.layers.37.linear_attn.norm.weight": "model-00013-of-00014.safetensors",
|
| 583 |
+
"language_model.model.layers.37.linear_attn.out_proj.weight": "model-00013-of-00014.safetensors",
|
| 584 |
+
"language_model.model.layers.37.mlp.gate.weight": "model-00013-of-00014.safetensors",
|
| 585 |
+
"language_model.model.layers.37.mlp.shared_expert.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 586 |
+
"language_model.model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 587 |
+
"language_model.model.layers.37.mlp.shared_expert.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 588 |
+
"language_model.model.layers.37.mlp.shared_expert_gate.weight": "model-00013-of-00014.safetensors",
|
| 589 |
+
"language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 590 |
+
"language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 591 |
+
"language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 592 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 593 |
+
"language_model.model.layers.38.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 594 |
+
"language_model.model.layers.38.linear_attn.A_log": "model-00013-of-00014.safetensors",
|
| 595 |
+
"language_model.model.layers.38.linear_attn.conv1d.weight": "model-00013-of-00014.safetensors",
|
| 596 |
+
"language_model.model.layers.38.linear_attn.dt_bias": "model-00013-of-00014.safetensors",
|
| 597 |
+
"language_model.model.layers.38.linear_attn.in_proj_a.weight": "model-00013-of-00014.safetensors",
|
| 598 |
+
"language_model.model.layers.38.linear_attn.in_proj_b.weight": "model-00013-of-00014.safetensors",
|
| 599 |
+
"language_model.model.layers.38.linear_attn.in_proj_qkv.weight": "model-00013-of-00014.safetensors",
|
| 600 |
+
"language_model.model.layers.38.linear_attn.in_proj_z.weight": "model-00013-of-00014.safetensors",
|
| 601 |
+
"language_model.model.layers.38.linear_attn.norm.weight": "model-00013-of-00014.safetensors",
|
| 602 |
+
"language_model.model.layers.38.linear_attn.out_proj.weight": "model-00013-of-00014.safetensors",
|
| 603 |
+
"language_model.model.layers.38.mlp.gate.weight": "model-00013-of-00014.safetensors",
|
| 604 |
+
"language_model.model.layers.38.mlp.shared_expert.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 605 |
+
"language_model.model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00014-of-00014.safetensors",
|
| 606 |
+
"language_model.model.layers.38.mlp.shared_expert.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 607 |
+
"language_model.model.layers.38.mlp.shared_expert_gate.weight": "model-00014-of-00014.safetensors",
|
| 608 |
+
"language_model.model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 609 |
+
"language_model.model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 610 |
+
"language_model.model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 611 |
+
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 612 |
+
"language_model.model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 613 |
+
"language_model.model.layers.39.mlp.gate.weight": "model-00014-of-00014.safetensors",
|
| 614 |
+
"language_model.model.layers.39.mlp.shared_expert.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 615 |
+
"language_model.model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00014-of-00014.safetensors",
|
| 616 |
+
"language_model.model.layers.39.mlp.shared_expert.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 617 |
+
"language_model.model.layers.39.mlp.shared_expert_gate.weight": "model-00014-of-00014.safetensors",
|
| 618 |
+
"language_model.model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 619 |
+
"language_model.model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
|
| 620 |
+
"language_model.model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 621 |
+
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 622 |
+
"language_model.model.layers.39.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
| 623 |
+
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
|
| 624 |
+
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
|
| 625 |
+
"language_model.model.layers.39.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
|
| 626 |
+
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
|
| 627 |
+
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
| 628 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 629 |
+
"language_model.model.layers.4.linear_attn.A_log": "model-00002-of-00014.safetensors",
|
| 630 |
+
"language_model.model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00014.safetensors",
|
| 631 |
+
"language_model.model.layers.4.linear_attn.dt_bias": "model-00002-of-00014.safetensors",
|
| 632 |
+
"language_model.model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00014.safetensors",
|
| 633 |
+
"language_model.model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00014.safetensors",
|
| 634 |
+
"language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00014.safetensors",
|
| 635 |
+
"language_model.model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00014.safetensors",
|
| 636 |
+
"language_model.model.layers.4.linear_attn.norm.weight": "model-00002-of-00014.safetensors",
|
| 637 |
+
"language_model.model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00014.safetensors",
|
| 638 |
+
"language_model.model.layers.4.mlp.gate.weight": "model-00002-of-00014.safetensors",
|
| 639 |
+
"language_model.model.layers.4.mlp.shared_expert.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 640 |
+
"language_model.model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 641 |
+
"language_model.model.layers.4.mlp.shared_expert.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 642 |
+
"language_model.model.layers.4.mlp.shared_expert_gate.weight": "model-00002-of-00014.safetensors",
|
| 643 |
+
"language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 644 |
+
"language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 645 |
+
"language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 646 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 647 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 648 |
+
"language_model.model.layers.5.linear_attn.A_log": "model-00002-of-00014.safetensors",
|
| 649 |
+
"language_model.model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00014.safetensors",
|
| 650 |
+
"language_model.model.layers.5.linear_attn.dt_bias": "model-00002-of-00014.safetensors",
|
| 651 |
+
"language_model.model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00014.safetensors",
|
| 652 |
+
"language_model.model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00014.safetensors",
|
| 653 |
+
"language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00014.safetensors",
|
| 654 |
+
"language_model.model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00014.safetensors",
|
| 655 |
+
"language_model.model.layers.5.linear_attn.norm.weight": "model-00002-of-00014.safetensors",
|
| 656 |
+
"language_model.model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00014.safetensors",
|
| 657 |
+
"language_model.model.layers.5.mlp.gate.weight": "model-00002-of-00014.safetensors",
|
| 658 |
+
"language_model.model.layers.5.mlp.shared_expert.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 659 |
+
"language_model.model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 660 |
+
"language_model.model.layers.5.mlp.shared_expert.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 661 |
+
"language_model.model.layers.5.mlp.shared_expert_gate.weight": "model-00003-of-00014.safetensors",
|
| 662 |
+
"language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 663 |
+
"language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 664 |
+
"language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 665 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 666 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 667 |
+
"language_model.model.layers.6.linear_attn.A_log": "model-00003-of-00014.safetensors",
|
| 668 |
+
"language_model.model.layers.6.linear_attn.conv1d.weight": "model-00003-of-00014.safetensors",
|
| 669 |
+
"language_model.model.layers.6.linear_attn.dt_bias": "model-00003-of-00014.safetensors",
|
| 670 |
+
"language_model.model.layers.6.linear_attn.in_proj_a.weight": "model-00003-of-00014.safetensors",
|
| 671 |
+
"language_model.model.layers.6.linear_attn.in_proj_b.weight": "model-00003-of-00014.safetensors",
|
| 672 |
+
"language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model-00003-of-00014.safetensors",
|
| 673 |
+
"language_model.model.layers.6.linear_attn.in_proj_z.weight": "model-00003-of-00014.safetensors",
|
| 674 |
+
"language_model.model.layers.6.linear_attn.norm.weight": "model-00003-of-00014.safetensors",
|
| 675 |
+
"language_model.model.layers.6.linear_attn.out_proj.weight": "model-00003-of-00014.safetensors",
|
| 676 |
+
"language_model.model.layers.6.mlp.gate.weight": "model-00003-of-00014.safetensors",
|
| 677 |
+
"language_model.model.layers.6.mlp.shared_expert.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 678 |
+
"language_model.model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 679 |
+
"language_model.model.layers.6.mlp.shared_expert.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 680 |
+
"language_model.model.layers.6.mlp.shared_expert_gate.weight": "model-00003-of-00014.safetensors",
|
| 681 |
+
"language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 682 |
+
"language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 683 |
+
"language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 684 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 685 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 686 |
+
"language_model.model.layers.7.mlp.gate.weight": "model-00003-of-00014.safetensors",
|
| 687 |
+
"language_model.model.layers.7.mlp.shared_expert.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 688 |
+
"language_model.model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 689 |
+
"language_model.model.layers.7.mlp.shared_expert.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 690 |
+
"language_model.model.layers.7.mlp.shared_expert_gate.weight": "model-00003-of-00014.safetensors",
|
| 691 |
+
"language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 692 |
+
"language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 693 |
+
"language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 694 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 695 |
+
"language_model.model.layers.7.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 696 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 697 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 698 |
+
"language_model.model.layers.7.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 699 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 700 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 701 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 702 |
+
"language_model.model.layers.8.linear_attn.A_log": "model-00003-of-00014.safetensors",
|
| 703 |
+
"language_model.model.layers.8.linear_attn.conv1d.weight": "model-00003-of-00014.safetensors",
|
| 704 |
+
"language_model.model.layers.8.linear_attn.dt_bias": "model-00003-of-00014.safetensors",
|
| 705 |
+
"language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00003-of-00014.safetensors",
|
| 706 |
+
"language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00003-of-00014.safetensors",
|
| 707 |
+
"language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00003-of-00014.safetensors",
|
| 708 |
+
"language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00003-of-00014.safetensors",
|
| 709 |
+
"language_model.model.layers.8.linear_attn.norm.weight": "model-00003-of-00014.safetensors",
|
| 710 |
+
"language_model.model.layers.8.linear_attn.out_proj.weight": "model-00003-of-00014.safetensors",
|
| 711 |
+
"language_model.model.layers.8.mlp.gate.weight": "model-00003-of-00014.safetensors",
|
| 712 |
+
"language_model.model.layers.8.mlp.shared_expert.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 713 |
+
"language_model.model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 714 |
+
"language_model.model.layers.8.mlp.shared_expert.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 715 |
+
"language_model.model.layers.8.mlp.shared_expert_gate.weight": "model-00004-of-00014.safetensors",
|
| 716 |
+
"language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 717 |
+
"language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 718 |
+
"language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 719 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 720 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 721 |
+
"language_model.model.layers.9.linear_attn.A_log": "model-00004-of-00014.safetensors",
|
| 722 |
+
"language_model.model.layers.9.linear_attn.conv1d.weight": "model-00004-of-00014.safetensors",
|
| 723 |
+
"language_model.model.layers.9.linear_attn.dt_bias": "model-00004-of-00014.safetensors",
|
| 724 |
+
"language_model.model.layers.9.linear_attn.in_proj_a.weight": "model-00004-of-00014.safetensors",
|
| 725 |
+
"language_model.model.layers.9.linear_attn.in_proj_b.weight": "model-00004-of-00014.safetensors",
|
| 726 |
+
"language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model-00004-of-00014.safetensors",
|
| 727 |
+
"language_model.model.layers.9.linear_attn.in_proj_z.weight": "model-00004-of-00014.safetensors",
|
| 728 |
+
"language_model.model.layers.9.linear_attn.norm.weight": "model-00004-of-00014.safetensors",
|
| 729 |
+
"language_model.model.layers.9.linear_attn.out_proj.weight": "model-00004-of-00014.safetensors",
|
| 730 |
+
"language_model.model.layers.9.mlp.gate.weight": "model-00004-of-00014.safetensors",
|
| 731 |
+
"language_model.model.layers.9.mlp.shared_expert.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 732 |
+
"language_model.model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 733 |
+
"language_model.model.layers.9.mlp.shared_expert.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 734 |
+
"language_model.model.layers.9.mlp.shared_expert_gate.weight": "model-00004-of-00014.safetensors",
|
| 735 |
+
"language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 736 |
+
"language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 737 |
+
"language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 738 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 739 |
+
"language_model.model.norm.weight": "model-00014-of-00014.safetensors"
|
| 740 |
+
}
|
| 741 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|vision_pad|>",
|
| 25 |
+
"padding_side": "right",
|
| 26 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 27 |
+
"processor_class": "Qwen3VLProcessor",
|
| 28 |
+
"split_special_tokens": false,
|
| 29 |
+
"tokenizer_class": "TokenizersBackend",
|
| 30 |
+
"tool_parser_type": "qwen3_coder",
|
| 31 |
+
"unk_token": null,
|
| 32 |
+
"video_token": "<|video_pad|>",
|
| 33 |
+
"vision_bos_token": "<|vision_start|>",
|
| 34 |
+
"vision_eos_token": "<|vision_end|>"
|
| 35 |
+
}
|