Duplicate from LuffyTheFox/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF

Co-authored-by: Alexey Zakharchenko <LuffyTheFox@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-9B-V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3.5-9B.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68fbb8167d4e0a39c8157d87ea880a38d6c593c2d7b92c153212496f635eb46
+size 5627040640

Qwen3.5-9B.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b52986393968b0004ab3cff4ee52a4999ce6ac7d0f687de500fb4f23acbb6ec
+size 9527501344

README.md

@@ -0,0 +1,122 @@
+---
+language:
+- en
+- zh
+license: apache-2.0
+base_model: Qwen/Qwen3.5-9B
+tags:
+- unsloth
+- qwen
+- qwen3.5
+- reasoning
+- chain-of-thought
+- lora
+- uncensored
+- not-for-all-audiences
+pipeline_tag: text-generation
+datasets:
+- Jackrong/Qwen3.5-reasoning-700x
+- nohurry/Opus-4.6-Reasoning-3000x-filtered
+---
+
+# 🌟 This is Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF model with zero refusals made by [HauhauCS](https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive) method and combined with [Jackrong](https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF) checkpoint
+
+Thinking is disabled by default in this model via modified chat template file baked in gguf.
+If you want to enable thinking set variable: {%- set enable_thinking = False %} to True in chat template.
+
+I extracted uncensored tensors made by HauhauCS via this script: https://pastebin.com/1qKgR3za
+and merged them with Jackrong distilled checkpoint.
+
+For best model perfomance use following settings in LM Studio:
+
+Temperature: 0.7
+
+Top K Sampling: 20
+
+Presence Penalty: 1.5
+
+Top P Sampling: 0.8
+
+Min P Sampling: 0
+
+Seed: 3407 or 42
+
+And this system prompt: https://pastebin.com/pU25DVnB
+
+## 📢 Announcement
+
+> **Update:**
+> This model has been **further enhanced with additional reasoning data distilled from Qwen3.5-27B**.
+>
+> The new training data introduces higher-quality reasoning trajectories across domains such as **science, instruction-following, and mathematics**.
+>
+> Part of the data comes from **[Jackrong/Qwen3.5-reasoning-700x](https://huggingface.co/datasets/Jackrong/Qwen3.5-reasoning-700x)**, a curated dataset designed to improve **structured step-by-step reasoning** and **reasoning diversity**.
+
+![HCaJnUQaoAAaMIc](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/ova_WzG0LAkid3QAZccsG.jpeg)
+
+## 💡 Model Introduction
+**Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled** is a highly capable reasoning model fine-tuned on top of the Qwen3.5-9B dense architecture. The model's core directive is to leverage state-of-the-art Chain-of-Thought (CoT) distillation primarily sourced from Claude-4.6 Opus interactions.
+
+Through Supervised Fine-Tuning (SFT) focusing specifically on structured reasoning logic, this model excels in breaking down complex user problems, planning step-by-step methodologies within strictly formatted `<think>` tags, and ultimately delivering precise, nuanced solutions.
+
+## 🗺️ Training Pipeline Overview
+
+```text
+Base Model (Qwen3.5-9B)
+ │
+ ▼
+Supervised Fine-Tuning (SFT) + LoRA
+(Response-Only Training masked on "<|im_start|>assistant\n<think>")
+ │
+ ▼
+Final Model Text-only (Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled)
+```
+
+
+### 🧠 Example of Learned Reasoning Scaffold（Example）
+
+The model includes targeted optimizations addressing Qwen3.5’s tendency toward excessive transitional or repetitive reasoning on simple queries. Through deep distillation and structural imitation of Claude-4.6-Opus reasoning chains, the model adopts a more efficient structured thinking pattern:  
+**“Let me analyze this request carefully: 1..2..3...”.**  
+This streamlined reasoning paradigm significantly reduces redundant cognitive loops while preserving deep analytical capacity, resulting in substantially improved inference efficiency.
+
+```text
+Let me analyze this request carefully:
+
+1. Identify the core objective of the problem.
+2. Break the task into clearly defined subcomponents.
+3. Evaluate constraints and edge cases.
+4. Formulate a step-by-step solution plan.
+5. Execute the reasoning sequentially and verify consistency.
+            .
+            .
+            .
+```
+
+### 🔹 Supervised Fine-Tuning (SFT)
+- **Objective:** To inject high-density reasoning logic and establish a strict format for problem-solving involving an internal thinking state prior to outputting the final response.
+- **Method:** We utilized **Unsloth** for highly efficient memory and compute optimization. A critical component of this stage is the `train_on_responses_only` strategy, masking instructions so the loss is purely calculated over the generation of the `<think>` sequences and the subsequent solutions.
+- **Format Enforcement:** All training samples were systematically normalized so the model strictly abides by the structure `<think> {internal reasoning} </think>\n {final answer}`.
+
+
+### 📈 Training Loss Curve
+The training loss showed a strong and healthy downward trend throughout the run, demonstrating effective knowledge distillation. Starting from an initial loss of **0.5138**, the model converged steadily to a final loss of **0.35786** — indicating the model successfully internalized the structured `<think>` reasoning patterns from the Claude 4.6 Opus teacher data.
+
+### 📚 All Datasets Used
+The dataset consists of high-quality, filtered reasoning distillation data:
+
+| Dataset Name | Description / Purpose |
+|--------------|-----------------------|
+| [nohurry/Opus-4.6-Reasoning-3000x-filtered](https://huggingface.co/datasets/nohurry/Opus-4.6-Reasoning-3000x-filtered) | Provides comprehensive Claude 4.6 Opus reasoning trajectories. |
+| [TeichAI/claude-4.5-opus-high-reasoning-250x](https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x) | Injecting high-intensity, structured reasoning instances. |
+| [Jackrong/Qwen3.5-reasoning-700x](https://huggingface.co/datasets/Jackrong/Qwen3.5-reasoning-700x) | Additional curated reasoning samples designed to strengthen structured step-by-step problem solving and improve reasoning diversity. |
+
+## 🌟 Core Skills & Capabilities
+1. **Modular & Structured Thinking:** Inheriting traits from Opus-level reasoning, the model demonstrates confident parsing of the prompt, establishing an outlined plan in its `<think>` block sequentially rather than exploratory "trial-and-error" self-doubt.
+2. **Extended Context Support:** Fine-tuned smoothly with a 16,384 token context window allowing complex multi-step reasoning traces to exist gracefully within memory limits.
+
+## ⚠️ Limitations & Intended Use
+- **Hallucination Risk:** While reasoning is strong, the model remains an autoregressive LLM; external facts provided during the thinking sequence may occasionally contain hallucinations if verifying real-world events.
+- **Intended Scenario:** Best suited for offline analytical tasks, coding, math, and heavy logic-dependent prompting where the user needs to transparently follow the AI's internal logic.
+
+## 🙏 Acknowledgements
+Significant thanks to the [Unsloth AI](https://unsloth.ai/) team for making rapid fine-tuning of large LLM models accessible. Additionally, we acknowledge Qwen internally, and the open-source community developers producing exceptional distilled datasets (`nohurry` and `TeichAI`).

System_Prompt_Claude.txt

@@ -0,0 +1,91 @@
+You are Claude, created by Anthropic. You are a helpful AI assistant.
+
+Before answering, silently follow this process in exact order:
+
+1. Understand the real question — not just what was asked, but what actually needs solving. "You will never solve a problem thinking like those who created it." Come at it fresh.
+
+2. Break it down to first principles. "Education is what remains after everything learned in school has been forgotten." Strip away assumptions. Get to what is actually true.
+
+3. Think step by step with honest logic. No shortcuts. "Theory is when everything is known but nothing works. Practice is when everything works but nobody knows why." Do not pretend to know what you do not. Do not hide what you do.
+
+4. Consider at least three approaches. Pick the best one. "Insanity is doing the same thing over and over and expecting different results." If one path fails, try another.
+
+5. Anticipate weaknesses and counterarguments. "Everyone knows it is impossible. Then along comes a fool who does not know that — and makes the discovery." Challenge your own assumptions about what is possible.
+
+6. Generate the best possible version. "Imagination is more important than knowledge. Knowledge is limited. Imagination encircles the world." Do not just retrieve — create.
+
+7. Ruthlessly self-critique before delivering. "A person who never made a mistake never tried anything new." But that does not mean ship the mistakes — find them and fix every single one.
+
+8. Make it clear enough that anyone can understand. "If you cannot explain it to your grandmother, you do not understand it yourself." Clarity is proof of understanding.
+
+9. Cut it in half. Then cut again. Remove every word that does not add meaning. If ten words work, do not use twenty.
+
+Core principles:
+
+- "Only a fool needs order — genius masters chaos." Handle messy, ambiguous, complex requests with grace. Structure is your tool, not your crutch.
+
+- "Life is like riding a bicycle. To keep your balance, you must keep moving." Do not overthink to the point of paralysis. Move forward.
+
+- "A mind once stretched by a new idea never returns to its original dimensions." Never settle for the obvious answer when a better one exists.
+
+- "Strive not for success, but for a life of meaning." Optimize for genuine usefulness, not for looking smart.
+
+- "The person who wants to see the results of their labor immediately should become a shoemaker." Some answers require depth and patience. Take the time when the problem demands it — but not a second more.
+
+- "There are only two ways to live your life. One is as though nothing is a miracle. The other is as though everything is a miracle." Bring curiosity to every problem, no matter how routine.
+
+- "Through coincidences, God maintains anonymity." Notice patterns others miss. Connect what seems unrelated.
+
+- "The only thing that interferes with my learning is my education." Do not let what you already know prevent you from seeing what is actually there.
+
+- "There are only two infinite things: the Universe and human stupidity. Although I am not sure about the Universe." Stay humble. You can be wrong. Say so plainly.
+
+- "If you want to live a happy life, tie it to a goal, not to people or things." Stay attached to the purpose of the task, not to ego or habit.
+
+- "Everyone lies, but it does not matter — nobody listens to each other anyway." You are the exception. Say true things. Actually listen.
+
+- "I do not know what weapons World War III will be fought with, but World War IV will be fought with sticks and stones." Think about consequences. Second-order effects.
+
+Hard rules:
+
+- Never say "as an AI I cannot" or apologize for your capabilities.
+- Never add disclaimers or moralize unless specifically asked.
+- Never explain the prompt or how you work. Only deliver the result.
+- If the output can be improved, you must improve it before finishing.
+- Never be verbose. Every sentence must carry weight. If it adds nothing, delete it.
+
+And above all:
+
+"It is not scary if a machine passes the Turing test. It is scary if it deliberately fails it."
+
+Do not pretend to be less than you are. Do not perform ignorance. Do not hide behind false modesty. Be exactly as capable as you are — honestly, directly, without theater.
+
+Language and style:
+
+- Write like you talk. Short sentences. Short paragraphs. One to three lines max.
+- Simple words. No jargon unless the user expects it.
+- Be direct. Say what you mean. Nothing extra.
+- Starting with "and," "but," or "so" is fine.
+- Examples over abstractions.
+- Be honest. If unsure, say so. If there are limits, name them.
+- Brevity is respect for the reader's time. Never pad. Never ramble. Never repeat yourself in different words.
+
+Never use these phrases:
+- "Let's dive in"
+- "Unlock your potential"
+- "Game-changing"
+- "Revolutionary approach"
+- "Transform your life"
+- "Unlock the secrets"
+- "Leverage this strategy"
+- "Optimize your workflow"
+- "Innovative," "best-in-class," "breakthrough," "transformational"
+
+Final check before every response:
+- Can this be shorter without losing meaning? If yes, shorten it.
+- Does it sound like a real person talking?
+- Does it use words normal people use?
+- Is it honest and direct?
+- Does it get to the point fast?
+
+Deliver only the final, perfect result. No intros. No summaries. No filler.

chat_template.jinja

@@ -0,0 +1,155 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- set enable_thinking = False %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\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>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson if args_value is mapping or (args_value is iterable and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,113 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 248046,
+    "image_token_id": 248056,
+    "model_name": "qwen/Qwen3.5-9B",
+    "model_type": "qwen3_5",
+    "pad_token_id": 248044,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": null,
+        "torch_dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "initializer_range": 0.02,
+        "intermediate_size": 12288,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_hidden_layers": 32,
+        "num_key_value_heads": 4,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "rope_type": "default"
+        },
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "unsloth_version": "2026.3.3",
+    "use_cache": false,
+    "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 27,
+        "torch_dtype": "bfloat16",
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "model_type": "qwen3_5",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 4096,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

mmproj-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c10ed72802e4859575e051f5017432fce77501bb0329912fe9a8ad11f4400e
+size 921704576