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

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

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"

w-ahmad commited on Jun 7

Commit

7884883

verified ·

1 Parent(s): 1791cd2

Upload MoQ-Tensor-Configs/MoQ_model_tensors_3.2.txt with huggingface_hub

Browse files

Files changed (1) hide show

MoQ-Tensor-Configs/MoQ_model_tensors_3.2.txt +40 -40

MoQ-Tensor-Configs/MoQ_model_tensors_3.2.txt CHANGED Viewed

@@ -62,9 +62,9 @@ blk.8.ffn_up.weight=IQ3_XXS
 blk.9.ffn_down.weight=IQ2_S
 blk.9.ffn_gate.weight=IQ2_S
 blk.9.ffn_up.weight=IQ3_XXS
-blk.0.attn_qkv.weight=IQ3_XXS
-blk.1.attn_qkv.weight=IQ3_XXS
-blk.10.attn_qkv.weight=IQ3_XXS
 blk.11.attn_q.weight=IQ4_XS
 blk.12.ffn_down.weight=IQ2_S
 blk.12.ffn_gate.weight=IQ2_S
@@ -72,32 +72,32 @@ blk.12.ffn_up.weight=IQ3_XXS
 blk.13.ffn_down.weight=IQ2_S
 blk.13.ffn_gate.weight=IQ2_S
 blk.13.ffn_up.weight=IQ3_XXS
-blk.14.attn_qkv.weight=IQ3_XXS
 blk.15.attn_q.weight=IQ4_XS
-blk.16.attn_qkv.weight=IQ3_XXS
-blk.17.attn_qkv.weight=IQ3_XXS
-blk.18.attn_qkv.weight=IQ3_XXS
 blk.19.ffn_gate.weight=IQ2_S
 blk.19.ffn_up.weight=IQ3_XXS
 blk.19.attn_q.weight=IQ4_XS
-blk.2.attn_qkv.weight=IQ3_XXS
 blk.2.ffn_down.weight=IQ2_S
 blk.2.ffn_gate.weight=IQ2_S
 blk.2.ffn_up.weight=IQ3_XXS
-blk.20.attn_qkv.weight=IQ3_XXS
 blk.20.ffn_down.weight=IQ2_S
 blk.20.ffn_gate.weight=IQ2_S
 blk.20.ffn_up.weight=IQ3_XXS
-blk.22.attn_qkv.weight=IQ3_XXS
 blk.23.attn_q.weight=IQ4_XS
-blk.24.attn_qkv.weight=IQ3_XXS
 blk.24.ffn_down.weight=IQ2_S
 blk.24.ffn_gate.weight=IQ2_S
 blk.24.ffn_up.weight=IQ3_XXS
-blk.25.attn_qkv.weight=IQ3_XXS
 blk.25.ffn_gate.weight=IQ2_S
 blk.25.ffn_up.weight=IQ3_XXS
-blk.26.attn_qkv.weight=IQ3_XXS
 blk.27.attn_q.weight=IQ4_XS
 blk.28.ffn_down.weight=IQ2_S
 blk.28.ffn_gate.weight=IQ2_S
@@ -106,14 +106,14 @@ blk.29.ffn_down.weight=IQ2_S
 blk.29.ffn_gate.weight=IQ2_S
 blk.29.ffn_up.weight=IQ3_XXS
 blk.3.attn_q.weight=IQ4_XS
-blk.30.attn_qkv.weight=IQ3_XXS
 blk.31.attn_q.weight=IQ4_XS
-blk.4.attn_qkv.weight=IQ3_XXS
-blk.5.attn_qkv.weight=IQ3_XXS
 blk.5.ffn_down.weight=IQ2_S
 blk.5.ffn_gate.weight=IQ2_S
 blk.5.ffn_up.weight=IQ3_XXS
-blk.6.attn_qkv.weight=IQ3_XXS
 blk.6.ffn_down.weight=IQ2_S
 blk.6.ffn_gate.weight=IQ2_S
 blk.6.ffn_up.weight=IQ3_XXS
@@ -121,8 +121,8 @@ blk.7.ffn_down.weight=IQ2_S
 blk.7.ffn_gate.weight=IQ2_S
 blk.7.ffn_up.weight=IQ3_XXS
 blk.7.attn_q.weight=IQ4_XS
-blk.8.attn_qkv.weight=IQ3_XXS
-blk.9.attn_qkv.weight=IQ3_XXS
 blk.0.ssm_alpha.weight=bf16
 blk.0.ssm_beta.weight=bf16
 blk.0.attn_gate.weight=IQ3_XXS
@@ -135,25 +135,25 @@ blk.10.ssm_alpha.weight=bf16
 blk.10.ssm_beta.weight=bf16
 blk.10.attn_gate.weight=IQ3_XXS
 blk.10.ssm_out.weight=IQ3_S
-blk.11.attn_k.weight=bf16
-blk.11.attn_output.weight=IQ4_XS
 blk.11.attn_v.weight=Q5_K
 blk.12.ssm_alpha.weight=bf16
 blk.12.ssm_beta.weight=bf16
-blk.12.attn_qkv.weight=IQ3_XXS
 blk.12.attn_gate.weight=IQ3_XXS
 blk.12.ssm_out.weight=IQ3_S
 blk.13.ssm_alpha.weight=bf16
 blk.13.ssm_beta.weight=bf16
-blk.13.attn_qkv.weight=IQ3_XXS
 blk.13.attn_gate.weight=IQ3_XXS
 blk.13.ssm_out.weight=IQ3_S
 blk.14.ssm_alpha.weight=bf16
 blk.14.ssm_beta.weight=bf16
 blk.14.attn_gate.weight=IQ3_XXS
 blk.14.ssm_out.weight=IQ3_S
-blk.15.attn_k.weight=bf16
-blk.15.attn_output.weight=IQ4_XS
 blk.15.attn_v.weight=Q5_K
 blk.16.ssm_alpha.weight=bf16
 blk.16.ssm_beta.weight=bf16
@@ -167,8 +167,8 @@ blk.18.ssm_alpha.weight=bf16
 blk.18.ssm_beta.weight=bf16
 blk.18.attn_gate.weight=IQ3_XXS
 blk.18.ssm_out.weight=IQ3_S
-blk.19.attn_k.weight=bf16
-blk.19.attn_output.weight=IQ4_XS
 blk.19.attn_v.weight=Q5_K
 blk.2.ssm_alpha.weight=bf16
 blk.2.ssm_beta.weight=bf16
@@ -180,15 +180,15 @@ blk.20.attn_gate.weight=IQ3_XXS
 blk.20.ssm_out.weight=IQ3_S
 blk.21.ssm_alpha.weight=bf16
 blk.21.ssm_beta.weight=bf16
-blk.21.attn_qkv.weight=IQ3_XXS
 blk.21.attn_gate.weight=IQ3_XXS
 blk.21.ssm_out.weight=IQ3_S
 blk.22.ssm_alpha.weight=bf16
 blk.22.ssm_beta.weight=bf16
 blk.22.attn_gate.weight=IQ3_XXS
 blk.22.ssm_out.weight=IQ3_S
-blk.23.attn_k.weight=bf16
-blk.23.attn_output.weight=IQ4_XS
 blk.23.attn_v.weight=Q5_K
 blk.24.ssm_alpha.weight=bf16
 blk.24.ssm_beta.weight=bf16
@@ -202,28 +202,28 @@ blk.26.ssm_alpha.weight=bf16
 blk.26.ssm_beta.weight=bf16
 blk.26.attn_gate.weight=IQ3_XXS
 blk.26.ssm_out.weight=IQ3_S
-blk.27.attn_k.weight=bf16
-blk.27.attn_output.weight=IQ4_XS
 blk.27.attn_v.weight=Q5_K
 blk.28.ssm_alpha.weight=bf16
 blk.28.ssm_beta.weight=bf16
-blk.28.attn_qkv.weight=IQ3_XXS
 blk.28.attn_gate.weight=IQ3_XXS
 blk.28.ssm_out.weight=IQ3_S
 blk.29.ssm_alpha.weight=bf16
 blk.29.ssm_beta.weight=bf16
-blk.29.attn_qkv.weight=IQ3_XXS
 blk.29.attn_gate.weight=IQ3_XXS
 blk.29.ssm_out.weight=IQ3_S
-blk.3.attn_k.weight=bf16
-blk.3.attn_output.weight=IQ4_XS
 blk.3.attn_v.weight=Q5_K
 blk.30.ssm_alpha.weight=bf16
 blk.30.ssm_beta.weight=bf16
 blk.30.attn_gate.weight=IQ3_XXS
 blk.30.ssm_out.weight=IQ3_S
-blk.31.attn_k.weight=bf16
-blk.31.attn_output.weight=IQ4_XS
 blk.31.attn_v.weight=Q5_K
 blk.4.ssm_alpha.weight=bf16
 blk.4.ssm_beta.weight=bf16
@@ -237,8 +237,8 @@ blk.6.ssm_alpha.weight=bf16
 blk.6.ssm_beta.weight=bf16
 blk.6.attn_gate.weight=IQ3_XXS
 blk.6.ssm_out.weight=IQ3_S
-blk.7.attn_k.weight=bf16
-blk.7.attn_output.weight=IQ4_XS
 blk.7.attn_v.weight=Q5_K
 blk.8.ssm_alpha.weight=bf16
 blk.8.ssm_beta.weight=bf16

 blk.9.ffn_down.weight=IQ2_S
 blk.9.ffn_gate.weight=IQ2_S
 blk.9.ffn_up.weight=IQ3_XXS
+blk.0.attn_qkv.weight=IQ3_S
+blk.1.attn_qkv.weight=IQ3_S
+blk.10.attn_qkv.weight=IQ3_S
 blk.11.attn_q.weight=IQ4_XS
 blk.12.ffn_down.weight=IQ2_S
 blk.12.ffn_gate.weight=IQ2_S
 blk.13.ffn_down.weight=IQ2_S
 blk.13.ffn_gate.weight=IQ2_S
 blk.13.ffn_up.weight=IQ3_XXS
+blk.14.attn_qkv.weight=IQ3_S
 blk.15.attn_q.weight=IQ4_XS
+blk.16.attn_qkv.weight=IQ3_S
+blk.17.attn_qkv.weight=IQ3_S
+blk.18.attn_qkv.weight=IQ3_S
 blk.19.ffn_gate.weight=IQ2_S
 blk.19.ffn_up.weight=IQ3_XXS
 blk.19.attn_q.weight=IQ4_XS
+blk.2.attn_qkv.weight=IQ3_S
 blk.2.ffn_down.weight=IQ2_S
 blk.2.ffn_gate.weight=IQ2_S
 blk.2.ffn_up.weight=IQ3_XXS
+blk.20.attn_qkv.weight=IQ3_S
 blk.20.ffn_down.weight=IQ2_S
 blk.20.ffn_gate.weight=IQ2_S
 blk.20.ffn_up.weight=IQ3_XXS
+blk.22.attn_qkv.weight=IQ3_S
 blk.23.attn_q.weight=IQ4_XS
+blk.24.attn_qkv.weight=IQ3_S
 blk.24.ffn_down.weight=IQ2_S
 blk.24.ffn_gate.weight=IQ2_S
 blk.24.ffn_up.weight=IQ3_XXS
+blk.25.attn_qkv.weight=IQ3_S
 blk.25.ffn_gate.weight=IQ2_S
 blk.25.ffn_up.weight=IQ3_XXS
+blk.26.attn_qkv.weight=IQ3_S
 blk.27.attn_q.weight=IQ4_XS
 blk.28.ffn_down.weight=IQ2_S
 blk.28.ffn_gate.weight=IQ2_S
 blk.29.ffn_gate.weight=IQ2_S
 blk.29.ffn_up.weight=IQ3_XXS
 blk.3.attn_q.weight=IQ4_XS
+blk.30.attn_qkv.weight=IQ3_S
 blk.31.attn_q.weight=IQ4_XS
+blk.4.attn_qkv.weight=IQ3_S
+blk.5.attn_qkv.weight=IQ3_S
 blk.5.ffn_down.weight=IQ2_S
 blk.5.ffn_gate.weight=IQ2_S
 blk.5.ffn_up.weight=IQ3_XXS
+blk.6.attn_qkv.weight=IQ3_S
 blk.6.ffn_down.weight=IQ2_S
 blk.6.ffn_gate.weight=IQ2_S
 blk.6.ffn_up.weight=IQ3_XXS
 blk.7.ffn_gate.weight=IQ2_S
 blk.7.ffn_up.weight=IQ3_XXS
 blk.7.attn_q.weight=IQ4_XS
+blk.8.attn_qkv.weight=IQ3_S
+blk.9.attn_qkv.weight=IQ3_S
 blk.0.ssm_alpha.weight=bf16
 blk.0.ssm_beta.weight=bf16
 blk.0.attn_gate.weight=IQ3_XXS
 blk.10.ssm_beta.weight=bf16
 blk.10.attn_gate.weight=IQ3_XXS
 blk.10.ssm_out.weight=IQ3_S
+blk.11.attn_k.weight=Q6_K
+blk.11.attn_output.weight=Q4_K
 blk.11.attn_v.weight=Q5_K
 blk.12.ssm_alpha.weight=bf16
 blk.12.ssm_beta.weight=bf16
+blk.12.attn_qkv.weight=IQ3_S
 blk.12.attn_gate.weight=IQ3_XXS
 blk.12.ssm_out.weight=IQ3_S
 blk.13.ssm_alpha.weight=bf16
 blk.13.ssm_beta.weight=bf16
+blk.13.attn_qkv.weight=IQ3_S
 blk.13.attn_gate.weight=IQ3_XXS
 blk.13.ssm_out.weight=IQ3_S
 blk.14.ssm_alpha.weight=bf16
 blk.14.ssm_beta.weight=bf16
 blk.14.attn_gate.weight=IQ3_XXS
 blk.14.ssm_out.weight=IQ3_S
+blk.15.attn_k.weight=Q6_K
+blk.15.attn_output.weight=Q4_K
 blk.15.attn_v.weight=Q5_K
 blk.16.ssm_alpha.weight=bf16
 blk.16.ssm_beta.weight=bf16
 blk.18.ssm_beta.weight=bf16
 blk.18.attn_gate.weight=IQ3_XXS
 blk.18.ssm_out.weight=IQ3_S
+blk.19.attn_k.weight=Q6_K
+blk.19.attn_output.weight=Q4_K
 blk.19.attn_v.weight=Q5_K
 blk.2.ssm_alpha.weight=bf16
 blk.2.ssm_beta.weight=bf16
 blk.20.ssm_out.weight=IQ3_S
 blk.21.ssm_alpha.weight=bf16
 blk.21.ssm_beta.weight=bf16
+blk.21.attn_qkv.weight=IQ3_S
 blk.21.attn_gate.weight=IQ3_XXS
 blk.21.ssm_out.weight=IQ3_S
 blk.22.ssm_alpha.weight=bf16
 blk.22.ssm_beta.weight=bf16
 blk.22.attn_gate.weight=IQ3_XXS
 blk.22.ssm_out.weight=IQ3_S
+blk.23.attn_k.weight=Q6_K
+blk.23.attn_output.weight=Q4_K
 blk.23.attn_v.weight=Q5_K
 blk.24.ssm_alpha.weight=bf16
 blk.24.ssm_beta.weight=bf16
 blk.26.ssm_beta.weight=bf16
 blk.26.attn_gate.weight=IQ3_XXS
 blk.26.ssm_out.weight=IQ3_S
+blk.27.attn_k.weight=Q6_K
+blk.27.attn_output.weight=Q4_K
 blk.27.attn_v.weight=Q5_K
 blk.28.ssm_alpha.weight=bf16
 blk.28.ssm_beta.weight=bf16
+blk.28.attn_qkv.weight=IQ3_S
 blk.28.attn_gate.weight=IQ3_XXS
 blk.28.ssm_out.weight=IQ3_S
 blk.29.ssm_alpha.weight=bf16
 blk.29.ssm_beta.weight=bf16
+blk.29.attn_qkv.weight=IQ3_S
 blk.29.attn_gate.weight=IQ3_XXS
 blk.29.ssm_out.weight=IQ3_S
+blk.3.attn_k.weight=Q6_K
+blk.3.attn_output.weight=Q4_K
 blk.3.attn_v.weight=Q5_K
 blk.30.ssm_alpha.weight=bf16
 blk.30.ssm_beta.weight=bf16
 blk.30.attn_gate.weight=IQ3_XXS
 blk.30.ssm_out.weight=IQ3_S
+blk.31.attn_k.weight=Q6_K
+blk.31.attn_output.weight=Q4_K
 blk.31.attn_v.weight=Q5_K
 blk.4.ssm_alpha.weight=bf16
 blk.4.ssm_beta.weight=bf16
 blk.6.ssm_beta.weight=bf16
 blk.6.attn_gate.weight=IQ3_XXS
 blk.6.ssm_out.weight=IQ3_S
+blk.7.attn_k.weight=Q6_K
+blk.7.attn_output.weight=Q4_K
 blk.7.attn_v.weight=Q5_K
 blk.8.ssm_alpha.weight=bf16
 blk.8.ssm_beta.weight=bf16