Instructions to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ", dtype="auto") - llama-cpp-python
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ", filename="MoQ-Quants/MoQ-3.0.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16 # Run inference directly in the terminal: llama cli -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16 # Run inference directly in the terminal: llama cli -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16 # Run inference directly in the terminal: ./llama-cli -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Use Docker
docker model run hf.co/w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
- LM Studio
- Jan
- Ollama
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with Ollama:
ollama run hf.co/w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
- Unsloth Studio
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ to start chatting
- Pi
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with Docker Model Runner:
docker model run hf.co/w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
- Lemonade
How to use w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull w-ahmad/Gemma-4-12B-it-qat-GGUF-MoQ:BF16
Run and chat with the model
lemonade run user.Gemma-4-12B-it-qat-GGUF-MoQ-BF16
List all available models
lemonade list
Upload MoQ-Tensor-Configs/MoQ_gemma4_12b_it_tensors_5.0.txt with huggingface_hub
Browse files
MoQ-Tensor-Configs/MoQ_gemma4_12b_it_tensors_5.0.txt
ADDED
|
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
token_embd.weight=IQ4_NL
|
| 2 |
+
blk.0.ffn_down.weight=Q4_K
|
| 3 |
+
blk.0.ffn_gate.weight=Q6_K
|
| 4 |
+
blk.0.ffn_up.weight=IQ4_NL
|
| 5 |
+
blk.0.attn_k.weight=Q4_K
|
| 6 |
+
blk.0.attn_output.weight=Q5_K
|
| 7 |
+
blk.0.attn_q.weight=IQ4_XS
|
| 8 |
+
blk.0.attn_v.weight=Q5_K
|
| 9 |
+
blk.1.ffn_down.weight=Q4_K
|
| 10 |
+
blk.1.ffn_gate.weight=Q6_K
|
| 11 |
+
blk.1.ffn_up.weight=IQ4_NL
|
| 12 |
+
blk.1.attn_k.weight=Q4_K
|
| 13 |
+
blk.1.attn_output.weight=Q5_K
|
| 14 |
+
blk.1.attn_q.weight=IQ4_XS
|
| 15 |
+
blk.1.attn_v.weight=Q5_K
|
| 16 |
+
blk.10.ffn_down.weight=Q4_K
|
| 17 |
+
blk.10.ffn_gate.weight=Q6_K
|
| 18 |
+
blk.10.ffn_up.weight=IQ4_NL
|
| 19 |
+
blk.10.attn_k.weight=Q4_K
|
| 20 |
+
blk.10.attn_output.weight=Q5_K
|
| 21 |
+
blk.10.attn_q.weight=IQ4_XS
|
| 22 |
+
blk.10.attn_v.weight=Q5_K
|
| 23 |
+
blk.11.ffn_down.weight=Q4_K
|
| 24 |
+
blk.11.ffn_gate.weight=Q6_K
|
| 25 |
+
blk.11.ffn_up.weight=IQ4_NL
|
| 26 |
+
blk.11.attn_k.weight=Q4_K
|
| 27 |
+
blk.11.attn_output.weight=Q5_K
|
| 28 |
+
blk.11.attn_q.weight=IQ4_XS
|
| 29 |
+
blk.12.ffn_down.weight=Q4_K
|
| 30 |
+
blk.12.ffn_gate.weight=Q6_K
|
| 31 |
+
blk.12.ffn_up.weight=IQ4_NL
|
| 32 |
+
blk.12.attn_k.weight=Q4_K
|
| 33 |
+
blk.12.attn_output.weight=Q5_K
|
| 34 |
+
blk.12.attn_q.weight=IQ4_XS
|
| 35 |
+
blk.12.attn_v.weight=Q5_K
|
| 36 |
+
blk.13.ffn_down.weight=Q4_K
|
| 37 |
+
blk.13.ffn_gate.weight=Q6_K
|
| 38 |
+
blk.13.ffn_up.weight=IQ4_NL
|
| 39 |
+
blk.13.attn_k.weight=Q4_K
|
| 40 |
+
blk.13.attn_output.weight=Q5_K
|
| 41 |
+
blk.13.attn_q.weight=IQ4_XS
|
| 42 |
+
blk.13.attn_v.weight=Q5_K
|
| 43 |
+
blk.14.ffn_down.weight=Q4_K
|
| 44 |
+
blk.14.ffn_gate.weight=Q6_K
|
| 45 |
+
blk.14.ffn_up.weight=IQ4_NL
|
| 46 |
+
blk.14.attn_k.weight=Q4_K
|
| 47 |
+
blk.14.attn_output.weight=Q5_K
|
| 48 |
+
blk.14.attn_q.weight=IQ4_XS
|
| 49 |
+
blk.14.attn_v.weight=Q5_K
|
| 50 |
+
blk.15.ffn_down.weight=Q4_K
|
| 51 |
+
blk.15.ffn_gate.weight=Q6_K
|
| 52 |
+
blk.15.ffn_up.weight=IQ4_NL
|
| 53 |
+
blk.15.attn_k.weight=Q4_K
|
| 54 |
+
blk.15.attn_output.weight=Q5_K
|
| 55 |
+
blk.15.attn_q.weight=IQ4_XS
|
| 56 |
+
blk.15.attn_v.weight=Q5_K
|
| 57 |
+
blk.16.ffn_down.weight=Q4_K
|
| 58 |
+
blk.16.ffn_gate.weight=Q6_K
|
| 59 |
+
blk.16.ffn_up.weight=IQ4_NL
|
| 60 |
+
blk.16.attn_k.weight=Q4_K
|
| 61 |
+
blk.16.attn_output.weight=Q5_K
|
| 62 |
+
blk.16.attn_q.weight=IQ4_XS
|
| 63 |
+
blk.16.attn_v.weight=Q5_K
|
| 64 |
+
blk.17.ffn_down.weight=Q4_K
|
| 65 |
+
blk.17.ffn_gate.weight=Q6_K
|
| 66 |
+
blk.17.ffn_up.weight=IQ4_NL
|
| 67 |
+
blk.17.attn_k.weight=Q4_K
|
| 68 |
+
blk.17.attn_output.weight=Q5_K
|
| 69 |
+
blk.17.attn_q.weight=IQ4_XS
|
| 70 |
+
blk.18.ffn_down.weight=Q4_K
|
| 71 |
+
blk.18.ffn_gate.weight=Q6_K
|
| 72 |
+
blk.18.ffn_up.weight=IQ4_NL
|
| 73 |
+
blk.18.attn_k.weight=Q4_K
|
| 74 |
+
blk.18.attn_output.weight=Q5_K
|
| 75 |
+
blk.18.attn_q.weight=IQ4_XS
|
| 76 |
+
blk.18.attn_v.weight=Q5_K
|
| 77 |
+
blk.19.ffn_down.weight=Q4_K
|
| 78 |
+
blk.19.ffn_gate.weight=Q6_K
|
| 79 |
+
blk.19.ffn_up.weight=IQ4_NL
|
| 80 |
+
blk.19.attn_k.weight=Q4_K
|
| 81 |
+
blk.19.attn_output.weight=Q5_K
|
| 82 |
+
blk.19.attn_q.weight=IQ4_XS
|
| 83 |
+
blk.19.attn_v.weight=Q5_K
|
| 84 |
+
blk.2.ffn_down.weight=Q4_K
|
| 85 |
+
blk.2.ffn_gate.weight=Q6_K
|
| 86 |
+
blk.2.ffn_up.weight=IQ4_NL
|
| 87 |
+
blk.2.attn_k.weight=Q4_K
|
| 88 |
+
blk.2.attn_output.weight=Q5_K
|
| 89 |
+
blk.2.attn_q.weight=IQ4_XS
|
| 90 |
+
blk.2.attn_v.weight=Q5_K
|
| 91 |
+
blk.20.ffn_down.weight=Q4_K
|
| 92 |
+
blk.20.ffn_gate.weight=Q6_K
|
| 93 |
+
blk.20.ffn_up.weight=IQ4_NL
|
| 94 |
+
blk.20.attn_k.weight=Q4_K
|
| 95 |
+
blk.20.attn_output.weight=Q5_K
|
| 96 |
+
blk.20.attn_q.weight=IQ4_XS
|
| 97 |
+
blk.20.attn_v.weight=Q5_K
|
| 98 |
+
blk.21.ffn_down.weight=Q4_K
|
| 99 |
+
blk.21.ffn_gate.weight=Q6_K
|
| 100 |
+
blk.21.ffn_up.weight=IQ4_NL
|
| 101 |
+
blk.21.attn_k.weight=Q4_K
|
| 102 |
+
blk.21.attn_output.weight=Q5_K
|
| 103 |
+
blk.21.attn_q.weight=IQ4_XS
|
| 104 |
+
blk.21.attn_v.weight=Q5_K
|
| 105 |
+
blk.22.ffn_down.weight=Q4_K
|
| 106 |
+
blk.22.ffn_gate.weight=Q6_K
|
| 107 |
+
blk.22.ffn_up.weight=IQ4_NL
|
| 108 |
+
blk.22.attn_k.weight=Q4_K
|
| 109 |
+
blk.22.attn_output.weight=Q5_K
|
| 110 |
+
blk.22.attn_q.weight=IQ4_XS
|
| 111 |
+
blk.22.attn_v.weight=Q5_K
|
| 112 |
+
blk.23.ffn_down.weight=Q4_K
|
| 113 |
+
blk.23.ffn_gate.weight=Q6_K
|
| 114 |
+
blk.23.ffn_up.weight=IQ4_NL
|
| 115 |
+
blk.23.attn_k.weight=Q4_K
|
| 116 |
+
blk.23.attn_output.weight=Q5_K
|
| 117 |
+
blk.23.attn_q.weight=IQ4_XS
|
| 118 |
+
blk.24.ffn_down.weight=Q4_K
|
| 119 |
+
blk.24.ffn_gate.weight=Q6_K
|
| 120 |
+
blk.24.ffn_up.weight=IQ4_NL
|
| 121 |
+
blk.24.attn_k.weight=Q4_K
|
| 122 |
+
blk.24.attn_output.weight=Q5_K
|
| 123 |
+
blk.24.attn_q.weight=IQ4_XS
|
| 124 |
+
blk.24.attn_v.weight=Q5_K
|
| 125 |
+
blk.25.ffn_down.weight=Q4_K
|
| 126 |
+
blk.25.ffn_gate.weight=Q6_K
|
| 127 |
+
blk.25.ffn_up.weight=IQ4_NL
|
| 128 |
+
blk.25.attn_k.weight=Q4_K
|
| 129 |
+
blk.25.attn_output.weight=Q5_K
|
| 130 |
+
blk.25.attn_q.weight=IQ4_XS
|
| 131 |
+
blk.25.attn_v.weight=Q5_K
|
| 132 |
+
blk.26.ffn_down.weight=Q4_K
|
| 133 |
+
blk.26.ffn_gate.weight=Q6_K
|
| 134 |
+
blk.26.ffn_up.weight=IQ4_NL
|
| 135 |
+
blk.26.attn_k.weight=Q4_K
|
| 136 |
+
blk.26.attn_output.weight=Q5_K
|
| 137 |
+
blk.26.attn_q.weight=IQ4_XS
|
| 138 |
+
blk.26.attn_v.weight=Q5_K
|
| 139 |
+
blk.27.ffn_down.weight=Q4_K
|
| 140 |
+
blk.27.ffn_gate.weight=Q6_K
|
| 141 |
+
blk.27.ffn_up.weight=IQ4_NL
|
| 142 |
+
blk.27.attn_k.weight=Q4_K
|
| 143 |
+
blk.27.attn_output.weight=Q5_K
|
| 144 |
+
blk.27.attn_q.weight=IQ4_XS
|
| 145 |
+
blk.27.attn_v.weight=Q5_K
|
| 146 |
+
blk.28.ffn_down.weight=Q4_K
|
| 147 |
+
blk.28.ffn_gate.weight=Q6_K
|
| 148 |
+
blk.28.ffn_up.weight=IQ4_NL
|
| 149 |
+
blk.28.attn_k.weight=Q4_K
|
| 150 |
+
blk.28.attn_output.weight=Q5_K
|
| 151 |
+
blk.28.attn_q.weight=IQ4_XS
|
| 152 |
+
blk.28.attn_v.weight=Q5_K
|
| 153 |
+
blk.29.ffn_down.weight=Q4_K
|
| 154 |
+
blk.29.ffn_gate.weight=Q6_K
|
| 155 |
+
blk.29.ffn_up.weight=IQ4_NL
|
| 156 |
+
blk.29.attn_k.weight=Q4_K
|
| 157 |
+
blk.29.attn_output.weight=Q5_K
|
| 158 |
+
blk.29.attn_q.weight=IQ4_XS
|
| 159 |
+
blk.3.ffn_down.weight=Q4_K
|
| 160 |
+
blk.3.ffn_gate.weight=Q6_K
|
| 161 |
+
blk.3.ffn_up.weight=IQ4_NL
|
| 162 |
+
blk.3.attn_k.weight=Q4_K
|
| 163 |
+
blk.3.attn_output.weight=Q5_K
|
| 164 |
+
blk.3.attn_q.weight=IQ4_XS
|
| 165 |
+
blk.3.attn_v.weight=Q5_K
|
| 166 |
+
blk.30.ffn_down.weight=Q4_K
|
| 167 |
+
blk.30.ffn_gate.weight=Q6_K
|
| 168 |
+
blk.30.ffn_up.weight=IQ4_NL
|
| 169 |
+
blk.30.attn_k.weight=Q4_K
|
| 170 |
+
blk.30.attn_output.weight=Q5_K
|
| 171 |
+
blk.30.attn_q.weight=IQ4_XS
|
| 172 |
+
blk.30.attn_v.weight=Q5_K
|
| 173 |
+
blk.31.ffn_down.weight=Q4_K
|
| 174 |
+
blk.31.ffn_gate.weight=Q6_K
|
| 175 |
+
blk.31.ffn_up.weight=IQ4_NL
|
| 176 |
+
blk.31.attn_k.weight=Q4_K
|
| 177 |
+
blk.31.attn_output.weight=Q5_K
|
| 178 |
+
blk.31.attn_q.weight=IQ4_XS
|
| 179 |
+
blk.31.attn_v.weight=Q5_K
|
| 180 |
+
blk.32.ffn_down.weight=Q4_K
|
| 181 |
+
blk.32.ffn_gate.weight=Q6_K
|
| 182 |
+
blk.32.ffn_up.weight=IQ4_NL
|
| 183 |
+
blk.32.attn_k.weight=Q4_K
|
| 184 |
+
blk.32.attn_output.weight=Q5_K
|
| 185 |
+
blk.32.attn_q.weight=IQ4_XS
|
| 186 |
+
blk.32.attn_v.weight=Q5_K
|
| 187 |
+
blk.33.ffn_down.weight=Q4_K
|
| 188 |
+
blk.33.ffn_gate.weight=Q6_K
|
| 189 |
+
blk.33.ffn_up.weight=IQ4_NL
|
| 190 |
+
blk.33.attn_k.weight=Q4_K
|
| 191 |
+
blk.33.attn_output.weight=Q5_K
|
| 192 |
+
blk.33.attn_q.weight=IQ4_XS
|
| 193 |
+
blk.33.attn_v.weight=Q5_K
|
| 194 |
+
blk.34.ffn_down.weight=Q4_K
|
| 195 |
+
blk.34.ffn_gate.weight=Q6_K
|
| 196 |
+
blk.34.ffn_up.weight=IQ4_NL
|
| 197 |
+
blk.34.attn_k.weight=Q4_K
|
| 198 |
+
blk.34.attn_output.weight=Q5_K
|
| 199 |
+
blk.34.attn_q.weight=IQ4_XS
|
| 200 |
+
blk.34.attn_v.weight=Q5_K
|
| 201 |
+
blk.35.ffn_down.weight=Q4_K
|
| 202 |
+
blk.35.ffn_gate.weight=Q6_K
|
| 203 |
+
blk.35.ffn_up.weight=IQ4_NL
|
| 204 |
+
blk.35.attn_k.weight=Q4_K
|
| 205 |
+
blk.35.attn_output.weight=Q5_K
|
| 206 |
+
blk.35.attn_q.weight=IQ4_XS
|
| 207 |
+
blk.36.ffn_down.weight=Q4_K
|
| 208 |
+
blk.36.ffn_gate.weight=Q6_K
|
| 209 |
+
blk.36.ffn_up.weight=IQ4_NL
|
| 210 |
+
blk.36.attn_k.weight=Q4_K
|
| 211 |
+
blk.36.attn_output.weight=Q5_K
|
| 212 |
+
blk.36.attn_q.weight=IQ4_XS
|
| 213 |
+
blk.36.attn_v.weight=Q5_K
|
| 214 |
+
blk.37.ffn_down.weight=Q4_K
|
| 215 |
+
blk.37.ffn_gate.weight=Q6_K
|
| 216 |
+
blk.37.ffn_up.weight=IQ4_NL
|
| 217 |
+
blk.37.attn_k.weight=Q4_K
|
| 218 |
+
blk.37.attn_output.weight=Q5_K
|
| 219 |
+
blk.37.attn_q.weight=IQ4_XS
|
| 220 |
+
blk.37.attn_v.weight=Q5_K
|
| 221 |
+
blk.38.ffn_down.weight=Q4_K
|
| 222 |
+
blk.38.ffn_gate.weight=Q6_K
|
| 223 |
+
blk.38.ffn_up.weight=IQ4_NL
|
| 224 |
+
blk.38.attn_k.weight=Q4_K
|
| 225 |
+
blk.38.attn_output.weight=Q5_K
|
| 226 |
+
blk.38.attn_q.weight=IQ4_XS
|
| 227 |
+
blk.38.attn_v.weight=Q5_K
|
| 228 |
+
blk.39.ffn_down.weight=Q4_K
|
| 229 |
+
blk.39.ffn_gate.weight=Q6_K
|
| 230 |
+
blk.39.ffn_up.weight=IQ4_NL
|
| 231 |
+
blk.39.attn_k.weight=Q4_K
|
| 232 |
+
blk.39.attn_output.weight=Q5_K
|
| 233 |
+
blk.39.attn_q.weight=IQ4_XS
|
| 234 |
+
blk.39.attn_v.weight=Q5_K
|
| 235 |
+
blk.4.ffn_down.weight=Q4_K
|
| 236 |
+
blk.4.ffn_gate.weight=Q6_K
|
| 237 |
+
blk.4.ffn_up.weight=IQ4_NL
|
| 238 |
+
blk.4.attn_k.weight=Q4_K
|
| 239 |
+
blk.4.attn_output.weight=Q5_K
|
| 240 |
+
blk.4.attn_q.weight=IQ4_XS
|
| 241 |
+
blk.4.attn_v.weight=Q5_K
|
| 242 |
+
blk.40.ffn_down.weight=Q4_K
|
| 243 |
+
blk.40.ffn_gate.weight=Q6_K
|
| 244 |
+
blk.40.ffn_up.weight=IQ4_NL
|
| 245 |
+
blk.40.attn_k.weight=Q4_K
|
| 246 |
+
blk.40.attn_output.weight=Q5_K
|
| 247 |
+
blk.40.attn_q.weight=IQ4_XS
|
| 248 |
+
blk.40.attn_v.weight=Q5_K
|
| 249 |
+
blk.41.ffn_down.weight=Q4_K
|
| 250 |
+
blk.41.ffn_gate.weight=Q6_K
|
| 251 |
+
blk.41.ffn_up.weight=IQ4_NL
|
| 252 |
+
blk.41.attn_k.weight=Q4_K
|
| 253 |
+
blk.41.attn_output.weight=Q5_K
|
| 254 |
+
blk.41.attn_q.weight=IQ4_XS
|
| 255 |
+
blk.42.ffn_down.weight=Q4_K
|
| 256 |
+
blk.42.ffn_gate.weight=Q6_K
|
| 257 |
+
blk.42.ffn_up.weight=IQ4_NL
|
| 258 |
+
blk.42.attn_k.weight=Q4_K
|
| 259 |
+
blk.42.attn_output.weight=Q5_K
|
| 260 |
+
blk.42.attn_q.weight=IQ4_XS
|
| 261 |
+
blk.42.attn_v.weight=Q5_K
|
| 262 |
+
blk.43.ffn_down.weight=Q4_K
|
| 263 |
+
blk.43.ffn_gate.weight=Q6_K
|
| 264 |
+
blk.43.ffn_up.weight=IQ4_NL
|
| 265 |
+
blk.43.attn_k.weight=Q4_K
|
| 266 |
+
blk.43.attn_output.weight=Q5_K
|
| 267 |
+
blk.43.attn_q.weight=IQ4_XS
|
| 268 |
+
blk.43.attn_v.weight=Q5_K
|
| 269 |
+
blk.44.ffn_down.weight=Q4_K
|
| 270 |
+
blk.44.ffn_gate.weight=Q6_K
|
| 271 |
+
blk.44.ffn_up.weight=IQ4_NL
|
| 272 |
+
blk.44.attn_k.weight=Q4_K
|
| 273 |
+
blk.44.attn_output.weight=Q5_K
|
| 274 |
+
blk.44.attn_q.weight=IQ4_XS
|
| 275 |
+
blk.44.attn_v.weight=Q5_K
|
| 276 |
+
blk.45.ffn_down.weight=Q4_K
|
| 277 |
+
blk.45.ffn_gate.weight=Q6_K
|
| 278 |
+
blk.45.ffn_up.weight=IQ4_NL
|
| 279 |
+
blk.45.attn_k.weight=Q4_K
|
| 280 |
+
blk.45.attn_output.weight=Q5_K
|
| 281 |
+
blk.45.attn_q.weight=IQ4_XS
|
| 282 |
+
blk.45.attn_v.weight=Q5_K
|
| 283 |
+
blk.46.ffn_down.weight=Q4_K
|
| 284 |
+
blk.46.ffn_gate.weight=Q6_K
|
| 285 |
+
blk.46.ffn_up.weight=IQ4_NL
|
| 286 |
+
blk.46.attn_k.weight=Q4_K
|
| 287 |
+
blk.46.attn_output.weight=Q5_K
|
| 288 |
+
blk.46.attn_q.weight=IQ4_XS
|
| 289 |
+
blk.46.attn_v.weight=Q5_K
|
| 290 |
+
blk.47.ffn_down.weight=Q4_K
|
| 291 |
+
blk.47.ffn_gate.weight=Q6_K
|
| 292 |
+
blk.47.ffn_up.weight=IQ4_NL
|
| 293 |
+
blk.47.attn_k.weight=Q4_K
|
| 294 |
+
blk.47.attn_output.weight=Q5_K
|
| 295 |
+
blk.47.attn_q.weight=IQ4_XS
|
| 296 |
+
blk.5.ffn_down.weight=Q4_K
|
| 297 |
+
blk.5.ffn_gate.weight=Q6_K
|
| 298 |
+
blk.5.ffn_up.weight=IQ4_NL
|
| 299 |
+
blk.5.attn_k.weight=Q4_K
|
| 300 |
+
blk.5.attn_output.weight=Q5_K
|
| 301 |
+
blk.5.attn_q.weight=IQ4_XS
|
| 302 |
+
blk.6.ffn_down.weight=Q4_K
|
| 303 |
+
blk.6.ffn_gate.weight=Q6_K
|
| 304 |
+
blk.6.ffn_up.weight=IQ4_NL
|
| 305 |
+
blk.6.attn_k.weight=Q4_K
|
| 306 |
+
blk.6.attn_output.weight=Q5_K
|
| 307 |
+
blk.6.attn_q.weight=IQ4_XS
|
| 308 |
+
blk.6.attn_v.weight=Q5_K
|
| 309 |
+
blk.7.ffn_down.weight=Q4_K
|
| 310 |
+
blk.7.ffn_gate.weight=Q6_K
|
| 311 |
+
blk.7.ffn_up.weight=IQ4_NL
|
| 312 |
+
blk.7.attn_k.weight=Q4_K
|
| 313 |
+
blk.7.attn_output.weight=Q5_K
|
| 314 |
+
blk.7.attn_q.weight=IQ4_XS
|
| 315 |
+
blk.7.attn_v.weight=Q5_K
|
| 316 |
+
blk.8.ffn_down.weight=Q4_K
|
| 317 |
+
blk.8.ffn_gate.weight=Q6_K
|
| 318 |
+
blk.8.ffn_up.weight=IQ4_NL
|
| 319 |
+
blk.8.attn_k.weight=Q4_K
|
| 320 |
+
blk.8.attn_output.weight=Q5_K
|
| 321 |
+
blk.8.attn_q.weight=IQ4_XS
|
| 322 |
+
blk.8.attn_v.weight=Q5_K
|
| 323 |
+
blk.9.ffn_down.weight=Q4_K
|
| 324 |
+
blk.9.ffn_gate.weight=Q6_K
|
| 325 |
+
blk.9.ffn_up.weight=IQ4_NL
|
| 326 |
+
blk.9.attn_k.weight=Q4_K
|
| 327 |
+
blk.9.attn_output.weight=Q5_K
|
| 328 |
+
blk.9.attn_q.weight=IQ4_XS
|
| 329 |
+
blk.9.attn_v.weight=Q5_K
|