Instructions to use w-ahmad/test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use w-ahmad/test 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/test # Run inference directly in the terminal: llama cli -hf w-ahmad/test
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf w-ahmad/test # Run inference directly in the terminal: llama cli -hf w-ahmad/test
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/test # Run inference directly in the terminal: ./llama-cli -hf w-ahmad/test
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/test # Run inference directly in the terminal: ./build/bin/llama-cli -hf w-ahmad/test
Use Docker
docker model run hf.co/w-ahmad/test
- LM Studio
- Jan
- Ollama
How to use w-ahmad/test with Ollama:
ollama run hf.co/w-ahmad/test
- Unsloth Desktop
- Pi
How to use w-ahmad/test 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/test
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/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/test" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use w-ahmad/test with Docker Model Runner:
docker model run hf.co/w-ahmad/test
- Lemonade
How to use w-ahmad/test with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull w-ahmad/test
Run and chat with the model
lemonade run user.test-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use w-ahmad/test 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/test
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/test
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use w-ahmad/test 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/test
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/test" \ --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"
Upload MoQ-Tensor-Configs/MoQ_model_tensors_3.8.txt with huggingface_hub
Browse files
MoQ-Tensor-Configs/MoQ_model_tensors_3.8.txt
ADDED
|
@@ -0,0 +1,250 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
output.weight=IQ4_XS
|
| 2 |
+
token_embd.weight=IQ4_XS
|
| 3 |
+
blk.14.ffn_down.weight=IQ3_S
|
| 4 |
+
blk.14.ffn_gate.weight=IQ3_S
|
| 5 |
+
blk.14.ffn_up.weight=IQ3_S
|
| 6 |
+
blk.15.ffn_down.weight=IQ3_S
|
| 7 |
+
blk.15.ffn_gate.weight=IQ3_S
|
| 8 |
+
blk.15.ffn_up.weight=IQ3_S
|
| 9 |
+
blk.25.ffn_down.weight=IQ3_S
|
| 10 |
+
blk.26.ffn_down.weight=IQ3_S
|
| 11 |
+
blk.26.ffn_gate.weight=IQ3_S
|
| 12 |
+
blk.26.ffn_up.weight=IQ3_S
|
| 13 |
+
blk.27.ffn_down.weight=IQ3_S
|
| 14 |
+
blk.27.ffn_gate.weight=IQ3_S
|
| 15 |
+
blk.0.ffn_down.weight=IQ3_S
|
| 16 |
+
blk.0.ffn_gate.weight=IQ3_S
|
| 17 |
+
blk.0.ffn_up.weight=IQ3_S
|
| 18 |
+
blk.1.ffn_down.weight=IQ3_S
|
| 19 |
+
blk.1.ffn_gate.weight=IQ3_S
|
| 20 |
+
blk.1.ffn_up.weight=IQ3_S
|
| 21 |
+
blk.10.ffn_down.weight=IQ3_S
|
| 22 |
+
blk.10.ffn_gate.weight=IQ3_S
|
| 23 |
+
blk.10.ffn_up.weight=IQ3_S
|
| 24 |
+
blk.11.ffn_down.weight=IQ3_S
|
| 25 |
+
blk.11.ffn_gate.weight=IQ3_S
|
| 26 |
+
blk.11.ffn_up.weight=IQ3_S
|
| 27 |
+
blk.16.ffn_down.weight=IQ3_S
|
| 28 |
+
blk.16.ffn_gate.weight=IQ3_S
|
| 29 |
+
blk.16.ffn_up.weight=IQ3_S
|
| 30 |
+
blk.17.ffn_down.weight=IQ3_S
|
| 31 |
+
blk.17.ffn_gate.weight=IQ3_S
|
| 32 |
+
blk.17.ffn_up.weight=IQ3_S
|
| 33 |
+
blk.18.ffn_down.weight=IQ3_S
|
| 34 |
+
blk.18.ffn_gate.weight=IQ3_S
|
| 35 |
+
blk.18.ffn_up.weight=IQ3_S
|
| 36 |
+
blk.19.ffn_down.weight=IQ3_S
|
| 37 |
+
blk.21.ffn_down.weight=IQ3_S
|
| 38 |
+
blk.21.ffn_gate.weight=IQ3_S
|
| 39 |
+
blk.21.ffn_up.weight=IQ3_S
|
| 40 |
+
blk.22.ffn_down.weight=IQ3_S
|
| 41 |
+
blk.22.ffn_gate.weight=IQ3_S
|
| 42 |
+
blk.22.ffn_up.weight=IQ3_S
|
| 43 |
+
blk.23.ffn_down.weight=IQ3_S
|
| 44 |
+
blk.23.ffn_gate.weight=IQ3_S
|
| 45 |
+
blk.23.ffn_up.weight=IQ3_S
|
| 46 |
+
blk.27.ffn_up.weight=IQ3_S
|
| 47 |
+
blk.3.ffn_down.weight=IQ3_S
|
| 48 |
+
blk.3.ffn_gate.weight=IQ3_S
|
| 49 |
+
blk.3.ffn_up.weight=IQ3_S
|
| 50 |
+
blk.30.ffn_down.weight=IQ3_S
|
| 51 |
+
blk.30.ffn_gate.weight=IQ3_S
|
| 52 |
+
blk.30.ffn_up.weight=IQ3_S
|
| 53 |
+
blk.31.ffn_down.weight=IQ3_S
|
| 54 |
+
blk.31.ffn_gate.weight=IQ3_S
|
| 55 |
+
blk.31.ffn_up.weight=IQ3_S
|
| 56 |
+
blk.4.ffn_down.weight=IQ3_S
|
| 57 |
+
blk.4.ffn_gate.weight=IQ3_S
|
| 58 |
+
blk.4.ffn_up.weight=IQ3_S
|
| 59 |
+
blk.8.ffn_down.weight=IQ3_S
|
| 60 |
+
blk.8.ffn_gate.weight=IQ3_S
|
| 61 |
+
blk.8.ffn_up.weight=IQ3_S
|
| 62 |
+
blk.9.ffn_down.weight=IQ3_S
|
| 63 |
+
blk.9.ffn_gate.weight=IQ3_S
|
| 64 |
+
blk.9.ffn_up.weight=IQ3_S
|
| 65 |
+
blk.0.attn_qkv.weight=IQ3_S
|
| 66 |
+
blk.1.attn_qkv.weight=IQ3_S
|
| 67 |
+
blk.10.attn_qkv.weight=IQ3_S
|
| 68 |
+
blk.11.attn_q.weight=IQ4_XS
|
| 69 |
+
blk.12.ffn_down.weight=IQ3_S
|
| 70 |
+
blk.12.ffn_gate.weight=IQ3_S
|
| 71 |
+
blk.12.ffn_up.weight=IQ3_S
|
| 72 |
+
blk.13.ffn_down.weight=IQ3_S
|
| 73 |
+
blk.13.ffn_gate.weight=IQ3_S
|
| 74 |
+
blk.13.ffn_up.weight=IQ3_S
|
| 75 |
+
blk.14.attn_qkv.weight=IQ3_S
|
| 76 |
+
blk.15.attn_q.weight=IQ4_XS
|
| 77 |
+
blk.16.attn_qkv.weight=IQ3_S
|
| 78 |
+
blk.17.attn_qkv.weight=IQ3_S
|
| 79 |
+
blk.18.attn_qkv.weight=IQ3_S
|
| 80 |
+
blk.19.ffn_gate.weight=IQ3_S
|
| 81 |
+
blk.19.ffn_up.weight=IQ3_S
|
| 82 |
+
blk.19.attn_q.weight=IQ4_XS
|
| 83 |
+
blk.2.attn_qkv.weight=IQ3_S
|
| 84 |
+
blk.2.ffn_down.weight=IQ3_S
|
| 85 |
+
blk.2.ffn_gate.weight=IQ3_S
|
| 86 |
+
blk.2.ffn_up.weight=IQ3_S
|
| 87 |
+
blk.20.attn_qkv.weight=IQ3_S
|
| 88 |
+
blk.20.ffn_down.weight=IQ3_S
|
| 89 |
+
blk.20.ffn_gate.weight=IQ3_S
|
| 90 |
+
blk.20.ffn_up.weight=IQ3_S
|
| 91 |
+
blk.22.attn_qkv.weight=IQ3_S
|
| 92 |
+
blk.23.attn_q.weight=IQ4_XS
|
| 93 |
+
blk.24.attn_qkv.weight=IQ3_S
|
| 94 |
+
blk.24.ffn_down.weight=IQ3_S
|
| 95 |
+
blk.24.ffn_gate.weight=IQ3_S
|
| 96 |
+
blk.24.ffn_up.weight=IQ3_S
|
| 97 |
+
blk.25.attn_qkv.weight=IQ3_S
|
| 98 |
+
blk.25.ffn_gate.weight=IQ3_S
|
| 99 |
+
blk.25.ffn_up.weight=IQ3_S
|
| 100 |
+
blk.26.attn_qkv.weight=IQ3_S
|
| 101 |
+
blk.27.attn_q.weight=IQ4_XS
|
| 102 |
+
blk.28.ffn_down.weight=IQ3_S
|
| 103 |
+
blk.28.ffn_gate.weight=IQ3_S
|
| 104 |
+
blk.28.ffn_up.weight=IQ3_S
|
| 105 |
+
blk.29.ffn_down.weight=IQ3_S
|
| 106 |
+
blk.29.ffn_gate.weight=IQ3_S
|
| 107 |
+
blk.29.ffn_up.weight=IQ3_S
|
| 108 |
+
blk.3.attn_q.weight=IQ4_XS
|
| 109 |
+
blk.30.attn_qkv.weight=IQ3_S
|
| 110 |
+
blk.31.attn_q.weight=IQ4_XS
|
| 111 |
+
blk.4.attn_qkv.weight=IQ3_S
|
| 112 |
+
blk.5.attn_qkv.weight=IQ3_S
|
| 113 |
+
blk.5.ffn_down.weight=IQ3_S
|
| 114 |
+
blk.5.ffn_gate.weight=IQ3_S
|
| 115 |
+
blk.5.ffn_up.weight=IQ3_S
|
| 116 |
+
blk.6.attn_qkv.weight=IQ3_S
|
| 117 |
+
blk.6.ffn_down.weight=IQ3_S
|
| 118 |
+
blk.6.ffn_gate.weight=IQ3_S
|
| 119 |
+
blk.6.ffn_up.weight=IQ3_S
|
| 120 |
+
blk.7.ffn_down.weight=IQ3_S
|
| 121 |
+
blk.7.ffn_gate.weight=IQ3_S
|
| 122 |
+
blk.7.ffn_up.weight=IQ3_S
|
| 123 |
+
blk.7.attn_q.weight=IQ4_XS
|
| 124 |
+
blk.8.attn_qkv.weight=IQ3_S
|
| 125 |
+
blk.9.attn_qkv.weight=IQ3_S
|
| 126 |
+
blk.0.ssm_alpha.weight=bf16
|
| 127 |
+
blk.0.ssm_beta.weight=bf16
|
| 128 |
+
blk.0.attn_gate.weight=IQ4_XS
|
| 129 |
+
blk.0.ssm_out.weight=IQ4_XS
|
| 130 |
+
blk.1.ssm_alpha.weight=bf16
|
| 131 |
+
blk.1.ssm_beta.weight=bf16
|
| 132 |
+
blk.1.attn_gate.weight=IQ4_XS
|
| 133 |
+
blk.1.ssm_out.weight=IQ4_XS
|
| 134 |
+
blk.10.ssm_alpha.weight=bf16
|
| 135 |
+
blk.10.ssm_beta.weight=bf16
|
| 136 |
+
blk.10.attn_gate.weight=IQ4_XS
|
| 137 |
+
blk.10.ssm_out.weight=IQ4_XS
|
| 138 |
+
blk.11.attn_k.weight=bf16
|
| 139 |
+
blk.11.attn_output.weight=Q4_K
|
| 140 |
+
blk.11.attn_v.weight=Q5_K
|
| 141 |
+
blk.12.ssm_alpha.weight=bf16
|
| 142 |
+
blk.12.ssm_beta.weight=bf16
|
| 143 |
+
blk.12.attn_qkv.weight=IQ3_S
|
| 144 |
+
blk.12.attn_gate.weight=IQ4_XS
|
| 145 |
+
blk.12.ssm_out.weight=IQ4_XS
|
| 146 |
+
blk.13.ssm_alpha.weight=bf16
|
| 147 |
+
blk.13.ssm_beta.weight=bf16
|
| 148 |
+
blk.13.attn_qkv.weight=IQ3_S
|
| 149 |
+
blk.13.attn_gate.weight=IQ4_XS
|
| 150 |
+
blk.13.ssm_out.weight=IQ4_XS
|
| 151 |
+
blk.14.ssm_alpha.weight=bf16
|
| 152 |
+
blk.14.ssm_beta.weight=bf16
|
| 153 |
+
blk.14.attn_gate.weight=IQ4_XS
|
| 154 |
+
blk.14.ssm_out.weight=IQ4_XS
|
| 155 |
+
blk.15.attn_k.weight=bf16
|
| 156 |
+
blk.15.attn_output.weight=Q4_K
|
| 157 |
+
blk.15.attn_v.weight=Q5_K
|
| 158 |
+
blk.16.ssm_alpha.weight=bf16
|
| 159 |
+
blk.16.ssm_beta.weight=bf16
|
| 160 |
+
blk.16.attn_gate.weight=IQ4_XS
|
| 161 |
+
blk.16.ssm_out.weight=IQ4_XS
|
| 162 |
+
blk.17.ssm_alpha.weight=bf16
|
| 163 |
+
blk.17.ssm_beta.weight=bf16
|
| 164 |
+
blk.17.attn_gate.weight=IQ4_XS
|
| 165 |
+
blk.17.ssm_out.weight=IQ4_XS
|
| 166 |
+
blk.18.ssm_alpha.weight=bf16
|
| 167 |
+
blk.18.ssm_beta.weight=bf16
|
| 168 |
+
blk.18.attn_gate.weight=IQ4_XS
|
| 169 |
+
blk.18.ssm_out.weight=IQ4_XS
|
| 170 |
+
blk.19.attn_k.weight=bf16
|
| 171 |
+
blk.19.attn_output.weight=Q4_K
|
| 172 |
+
blk.19.attn_v.weight=Q5_K
|
| 173 |
+
blk.2.ssm_alpha.weight=bf16
|
| 174 |
+
blk.2.ssm_beta.weight=bf16
|
| 175 |
+
blk.2.attn_gate.weight=IQ4_XS
|
| 176 |
+
blk.2.ssm_out.weight=IQ4_XS
|
| 177 |
+
blk.20.ssm_alpha.weight=bf16
|
| 178 |
+
blk.20.ssm_beta.weight=bf16
|
| 179 |
+
blk.20.attn_gate.weight=IQ4_XS
|
| 180 |
+
blk.20.ssm_out.weight=IQ4_XS
|
| 181 |
+
blk.21.ssm_alpha.weight=bf16
|
| 182 |
+
blk.21.ssm_beta.weight=bf16
|
| 183 |
+
blk.21.attn_qkv.weight=IQ3_S
|
| 184 |
+
blk.21.attn_gate.weight=IQ4_XS
|
| 185 |
+
blk.21.ssm_out.weight=IQ4_XS
|
| 186 |
+
blk.22.ssm_alpha.weight=bf16
|
| 187 |
+
blk.22.ssm_beta.weight=bf16
|
| 188 |
+
blk.22.attn_gate.weight=IQ4_XS
|
| 189 |
+
blk.22.ssm_out.weight=IQ4_XS
|
| 190 |
+
blk.23.attn_k.weight=bf16
|
| 191 |
+
blk.23.attn_output.weight=Q4_K
|
| 192 |
+
blk.23.attn_v.weight=Q5_K
|
| 193 |
+
blk.24.ssm_alpha.weight=bf16
|
| 194 |
+
blk.24.ssm_beta.weight=bf16
|
| 195 |
+
blk.24.attn_gate.weight=IQ4_XS
|
| 196 |
+
blk.24.ssm_out.weight=IQ4_XS
|
| 197 |
+
blk.25.ssm_alpha.weight=bf16
|
| 198 |
+
blk.25.ssm_beta.weight=bf16
|
| 199 |
+
blk.25.attn_gate.weight=IQ4_XS
|
| 200 |
+
blk.25.ssm_out.weight=IQ4_XS
|
| 201 |
+
blk.26.ssm_alpha.weight=bf16
|
| 202 |
+
blk.26.ssm_beta.weight=bf16
|
| 203 |
+
blk.26.attn_gate.weight=IQ4_XS
|
| 204 |
+
blk.26.ssm_out.weight=IQ4_XS
|
| 205 |
+
blk.27.attn_k.weight=bf16
|
| 206 |
+
blk.27.attn_output.weight=Q4_K
|
| 207 |
+
blk.27.attn_v.weight=Q5_K
|
| 208 |
+
blk.28.ssm_alpha.weight=bf16
|
| 209 |
+
blk.28.ssm_beta.weight=bf16
|
| 210 |
+
blk.28.attn_qkv.weight=IQ3_S
|
| 211 |
+
blk.28.attn_gate.weight=IQ4_XS
|
| 212 |
+
blk.28.ssm_out.weight=IQ4_XS
|
| 213 |
+
blk.29.ssm_alpha.weight=bf16
|
| 214 |
+
blk.29.ssm_beta.weight=bf16
|
| 215 |
+
blk.29.attn_qkv.weight=IQ3_S
|
| 216 |
+
blk.29.attn_gate.weight=IQ4_XS
|
| 217 |
+
blk.29.ssm_out.weight=IQ4_XS
|
| 218 |
+
blk.3.attn_k.weight=bf16
|
| 219 |
+
blk.3.attn_output.weight=Q4_K
|
| 220 |
+
blk.3.attn_v.weight=Q5_K
|
| 221 |
+
blk.30.ssm_alpha.weight=bf16
|
| 222 |
+
blk.30.ssm_beta.weight=bf16
|
| 223 |
+
blk.30.attn_gate.weight=IQ4_XS
|
| 224 |
+
blk.30.ssm_out.weight=IQ4_XS
|
| 225 |
+
blk.31.attn_k.weight=bf16
|
| 226 |
+
blk.31.attn_output.weight=Q4_K
|
| 227 |
+
blk.31.attn_v.weight=Q5_K
|
| 228 |
+
blk.4.ssm_alpha.weight=bf16
|
| 229 |
+
blk.4.ssm_beta.weight=bf16
|
| 230 |
+
blk.4.attn_gate.weight=IQ4_XS
|
| 231 |
+
blk.4.ssm_out.weight=IQ4_XS
|
| 232 |
+
blk.5.ssm_alpha.weight=bf16
|
| 233 |
+
blk.5.ssm_beta.weight=bf16
|
| 234 |
+
blk.5.attn_gate.weight=IQ4_XS
|
| 235 |
+
blk.5.ssm_out.weight=IQ4_XS
|
| 236 |
+
blk.6.ssm_alpha.weight=bf16
|
| 237 |
+
blk.6.ssm_beta.weight=bf16
|
| 238 |
+
blk.6.attn_gate.weight=IQ4_XS
|
| 239 |
+
blk.6.ssm_out.weight=IQ4_XS
|
| 240 |
+
blk.7.attn_k.weight=bf16
|
| 241 |
+
blk.7.attn_output.weight=Q4_K
|
| 242 |
+
blk.7.attn_v.weight=Q5_K
|
| 243 |
+
blk.8.ssm_alpha.weight=bf16
|
| 244 |
+
blk.8.ssm_beta.weight=bf16
|
| 245 |
+
blk.8.attn_gate.weight=IQ4_XS
|
| 246 |
+
blk.8.ssm_out.weight=IQ4_XS
|
| 247 |
+
blk.9.ssm_alpha.weight=bf16
|
| 248 |
+
blk.9.ssm_beta.weight=bf16
|
| 249 |
+
blk.9.attn_gate.weight=IQ4_XS
|
| 250 |
+
blk.9.ssm_out.weight=IQ4_XS
|