Instructions to use mkleinegger/tmp 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 mkleinegger/tmp 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 mkleinegger/tmp:IQ1_M # Run inference directly in the terminal: llama cli -hf mkleinegger/tmp:IQ1_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mkleinegger/tmp:IQ1_M # Run inference directly in the terminal: llama cli -hf mkleinegger/tmp:IQ1_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf mkleinegger/tmp:IQ1_M # Run inference directly in the terminal: ./build/bin/llama cli -hf mkleinegger/tmp:IQ1_M
Use Docker
docker model run hf.co/mkleinegger/tmp:IQ1_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use mkleinegger/tmp with Ollama:
ollama run hf.co/mkleinegger/tmp:IQ1_M
- Unsloth Desktop
- Pi
How to use mkleinegger/tmp with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf mkleinegger/tmp:IQ1_M
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": "mkleinegger/tmp:IQ1_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use mkleinegger/tmp with Docker Model Runner:
docker model run hf.co/mkleinegger/tmp:IQ1_M
- Lemonade
How to use mkleinegger/tmp with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mkleinegger/tmp:IQ1_M
Run and chat with the model
lemonade run user.tmp-IQ1_M
List all available models
lemonade list
- Hermes Agent
How to use mkleinegger/tmp with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf mkleinegger/tmp:IQ1_M
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 mkleinegger/tmp:IQ1_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use mkleinegger/tmp with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf mkleinegger/tmp:IQ1_M
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 "mkleinegger/tmp:IQ1_M" \ --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"
Download model-metadata/hf_linear_modules_38-27b.json from mkleinegger/tmp: direct link, hf CLI and curl.
- Browser
- Download file 25.2 kB
-
https://huggingface.co/mkleinegger/tmp/resolve/main/model-metadata/hf_linear_modules_38-27b.json
- Command line
-
hf download hf://mkleinegger/tmp/model-metadata/hf_linear_modules_38-27b.json
-
curl -L -o hf_linear_modules_38-27b.json https://huggingface.co/mkleinegger/tmp/resolve/main/model-metadata/hf_linear_modules_38-27b.json
25.2 kB
{
"linears": {
"lm_head": [
248320,
5120
],
"model.embed_tokens": [
248320,
5120
],
"model.layers.0.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.0.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.0.linear_attn.out_proj": [
5120,
6144
],
"model.layers.0.mlp.down_proj": [
5120,
17408
],
"model.layers.0.mlp.gate_proj": [
17408,
5120
],
"model.layers.0.mlp.up_proj": [
17408,
5120
],
"model.layers.1.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.1.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.1.linear_attn.out_proj": [
5120,
6144
],
"model.layers.1.mlp.down_proj": [
5120,
17408
],
"model.layers.1.mlp.gate_proj": [
17408,
5120
],
"model.layers.1.mlp.up_proj": [
17408,
5120
],
"model.layers.10.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.10.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.10.linear_attn.out_proj": [
5120,
6144
],
"model.layers.10.mlp.down_proj": [
5120,
17408
],
"model.layers.10.mlp.gate_proj": [
17408,
5120
],
"model.layers.10.mlp.up_proj": [
17408,
5120
],
"model.layers.11.mlp.down_proj": [
5120,
17408
],
"model.layers.11.mlp.gate_proj": [
17408,
5120
],
"model.layers.11.mlp.up_proj": [
17408,
5120
],
"model.layers.11.self_attn.k_proj": [
1024,
5120
],
"model.layers.11.self_attn.o_proj": [
5120,
6144
],
"model.layers.11.self_attn.q_proj": [
12288,
5120
],
"model.layers.11.self_attn.v_proj": [
1024,
5120
],
"model.layers.12.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.12.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.12.linear_attn.out_proj": [
5120,
6144
],
"model.layers.12.mlp.down_proj": [
5120,
17408
],
"model.layers.12.mlp.gate_proj": [
17408,
5120
],
"model.layers.12.mlp.up_proj": [
17408,
5120
],
"model.layers.13.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.13.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.13.linear_attn.out_proj": [
5120,
6144
],
"model.layers.13.mlp.down_proj": [
5120,
17408
],
"model.layers.13.mlp.gate_proj": [
17408,
5120
],
"model.layers.13.mlp.up_proj": [
17408,
5120
],
"model.layers.14.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.14.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.14.linear_attn.out_proj": [
5120,
6144
],
"model.layers.14.mlp.down_proj": [
5120,
17408
],
"model.layers.14.mlp.gate_proj": [
17408,
5120
],
"model.layers.14.mlp.up_proj": [
17408,
5120
],
"model.layers.15.mlp.down_proj": [
5120,
17408
],
"model.layers.15.mlp.gate_proj": [
17408,
5120
],
"model.layers.15.mlp.up_proj": [
17408,
5120
],
"model.layers.15.self_attn.k_proj": [
1024,
5120
],
"model.layers.15.self_attn.o_proj": [
5120,
6144
],
"model.layers.15.self_attn.q_proj": [
12288,
5120
],
"model.layers.15.self_attn.v_proj": [
1024,
5120
],
"model.layers.16.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.16.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.16.linear_attn.out_proj": [
5120,
6144
],
"model.layers.16.mlp.down_proj": [
5120,
17408
],
"model.layers.16.mlp.gate_proj": [
17408,
5120
],
"model.layers.16.mlp.up_proj": [
17408,
5120
],
"model.layers.17.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.17.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.17.linear_attn.out_proj": [
5120,
6144
],
"model.layers.17.mlp.down_proj": [
5120,
17408
],
"model.layers.17.mlp.gate_proj": [
17408,
5120
],
"model.layers.17.mlp.up_proj": [
17408,
5120
],
"model.layers.18.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.18.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.18.linear_attn.out_proj": [
5120,
6144
],
"model.layers.18.mlp.down_proj": [
5120,
17408
],
"model.layers.18.mlp.gate_proj": [
17408,
5120
],
"model.layers.18.mlp.up_proj": [
17408,
5120
],
"model.layers.19.mlp.down_proj": [
5120,
17408
],
"model.layers.19.mlp.gate_proj": [
17408,
5120
],
"model.layers.19.mlp.up_proj": [
17408,
5120
],
"model.layers.19.self_attn.k_proj": [
1024,
5120
],
"model.layers.19.self_attn.o_proj": [
5120,
6144
],
"model.layers.19.self_attn.q_proj": [
12288,
5120
],
"model.layers.19.self_attn.v_proj": [
1024,
5120
],
"model.layers.2.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.2.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.2.linear_attn.out_proj": [
5120,
6144
],
"model.layers.2.mlp.down_proj": [
5120,
17408
],
"model.layers.2.mlp.gate_proj": [
17408,
5120
],
"model.layers.2.mlp.up_proj": [
17408,
5120
],
"model.layers.20.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.20.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.20.linear_attn.out_proj": [
5120,
6144
],
"model.layers.20.mlp.down_proj": [
5120,
17408
],
"model.layers.20.mlp.gate_proj": [
17408,
5120
],
"model.layers.20.mlp.up_proj": [
17408,
5120
],
"model.layers.21.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.21.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.21.linear_attn.out_proj": [
5120,
6144
],
"model.layers.21.mlp.down_proj": [
5120,
17408
],
"model.layers.21.mlp.gate_proj": [
17408,
5120
],
"model.layers.21.mlp.up_proj": [
17408,
5120
],
"model.layers.22.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.22.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.22.linear_attn.out_proj": [
5120,
6144
],
"model.layers.22.mlp.down_proj": [
5120,
17408
],
"model.layers.22.mlp.gate_proj": [
17408,
5120
],
"model.layers.22.mlp.up_proj": [
17408,
5120
],
"model.layers.23.mlp.down_proj": [
5120,
17408
],
"model.layers.23.mlp.gate_proj": [
17408,
5120
],
"model.layers.23.mlp.up_proj": [
17408,
5120
],
"model.layers.23.self_attn.k_proj": [
1024,
5120
],
"model.layers.23.self_attn.o_proj": [
5120,
6144
],
"model.layers.23.self_attn.q_proj": [
12288,
5120
],
"model.layers.23.self_attn.v_proj": [
1024,
5120
],
"model.layers.24.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.24.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.24.linear_attn.out_proj": [
5120,
6144
],
"model.layers.24.mlp.down_proj": [
5120,
17408
],
"model.layers.24.mlp.gate_proj": [
17408,
5120
],
"model.layers.24.mlp.up_proj": [
17408,
5120
],
"model.layers.25.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.25.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.25.linear_attn.out_proj": [
5120,
6144
],
"model.layers.25.mlp.down_proj": [
5120,
17408
],
"model.layers.25.mlp.gate_proj": [
17408,
5120
],
"model.layers.25.mlp.up_proj": [
17408,
5120
],
"model.layers.26.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.26.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.26.linear_attn.out_proj": [
5120,
6144
],
"model.layers.26.mlp.down_proj": [
5120,
17408
],
"model.layers.26.mlp.gate_proj": [
17408,
5120
],
"model.layers.26.mlp.up_proj": [
17408,
5120
],
"model.layers.27.mlp.down_proj": [
5120,
17408
],
"model.layers.27.mlp.gate_proj": [
17408,
5120
],
"model.layers.27.mlp.up_proj": [
17408,
5120
],
"model.layers.27.self_attn.k_proj": [
1024,
5120
],
"model.layers.27.self_attn.o_proj": [
5120,
6144
],
"model.layers.27.self_attn.q_proj": [
12288,
5120
],
"model.layers.27.self_attn.v_proj": [
1024,
5120
],
"model.layers.28.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.28.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.28.linear_attn.out_proj": [
5120,
6144
],
"model.layers.28.mlp.down_proj": [
5120,
17408
],
"model.layers.28.mlp.gate_proj": [
17408,
5120
],
"model.layers.28.mlp.up_proj": [
17408,
5120
],
"model.layers.29.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.29.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.29.linear_attn.out_proj": [
5120,
6144
],
"model.layers.29.mlp.down_proj": [
5120,
17408
],
"model.layers.29.mlp.gate_proj": [
17408,
5120
],
"model.layers.29.mlp.up_proj": [
17408,
5120
],
"model.layers.3.mlp.down_proj": [
5120,
17408
],
"model.layers.3.mlp.gate_proj": [
17408,
5120
],
"model.layers.3.mlp.up_proj": [
17408,
5120
],
"model.layers.3.self_attn.k_proj": [
1024,
5120
],
"model.layers.3.self_attn.o_proj": [
5120,
6144
],
"model.layers.3.self_attn.q_proj": [
12288,
5120
],
"model.layers.3.self_attn.v_proj": [
1024,
5120
],
"model.layers.30.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.30.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.30.linear_attn.out_proj": [
5120,
6144
],
"model.layers.30.mlp.down_proj": [
5120,
17408
],
"model.layers.30.mlp.gate_proj": [
17408,
5120
],
"model.layers.30.mlp.up_proj": [
17408,
5120
],
"model.layers.31.mlp.down_proj": [
5120,
17408
],
"model.layers.31.mlp.gate_proj": [
17408,
5120
],
"model.layers.31.mlp.up_proj": [
17408,
5120
],
"model.layers.31.self_attn.k_proj": [
1024,
5120
],
"model.layers.31.self_attn.o_proj": [
5120,
6144
],
"model.layers.31.self_attn.q_proj": [
12288,
5120
],
"model.layers.31.self_attn.v_proj": [
1024,
5120
],
"model.layers.32.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.32.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.32.linear_attn.out_proj": [
5120,
6144
],
"model.layers.32.mlp.down_proj": [
5120,
17408
],
"model.layers.32.mlp.gate_proj": [
17408,
5120
],
"model.layers.32.mlp.up_proj": [
17408,
5120
],
"model.layers.33.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.33.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.33.linear_attn.out_proj": [
5120,
6144
],
"model.layers.33.mlp.down_proj": [
5120,
17408
],
"model.layers.33.mlp.gate_proj": [
17408,
5120
],
"model.layers.33.mlp.up_proj": [
17408,
5120
],
"model.layers.34.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.34.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.34.linear_attn.out_proj": [
5120,
6144
],
"model.layers.34.mlp.down_proj": [
5120,
17408
],
"model.layers.34.mlp.gate_proj": [
17408,
5120
],
"model.layers.34.mlp.up_proj": [
17408,
5120
],
"model.layers.35.mlp.down_proj": [
5120,
17408
],
"model.layers.35.mlp.gate_proj": [
17408,
5120
],
"model.layers.35.mlp.up_proj": [
17408,
5120
],
"model.layers.35.self_attn.k_proj": [
1024,
5120
],
"model.layers.35.self_attn.o_proj": [
5120,
6144
],
"model.layers.35.self_attn.q_proj": [
12288,
5120
],
"model.layers.35.self_attn.v_proj": [
1024,
5120
],
"model.layers.36.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.36.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.36.linear_attn.out_proj": [
5120,
6144
],
"model.layers.36.mlp.down_proj": [
5120,
17408
],
"model.layers.36.mlp.gate_proj": [
17408,
5120
],
"model.layers.36.mlp.up_proj": [
17408,
5120
],
"model.layers.37.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.37.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.37.linear_attn.out_proj": [
5120,
6144
],
"model.layers.37.mlp.down_proj": [
5120,
17408
],
"model.layers.37.mlp.gate_proj": [
17408,
5120
],
"model.layers.37.mlp.up_proj": [
17408,
5120
],
"model.layers.38.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.38.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.38.linear_attn.out_proj": [
5120,
6144
],
"model.layers.38.mlp.down_proj": [
5120,
17408
],
"model.layers.38.mlp.gate_proj": [
17408,
5120
],
"model.layers.38.mlp.up_proj": [
17408,
5120
],
"model.layers.39.mlp.down_proj": [
5120,
17408
],
"model.layers.39.mlp.gate_proj": [
17408,
5120
],
"model.layers.39.mlp.up_proj": [
17408,
5120
],
"model.layers.39.self_attn.k_proj": [
1024,
5120
],
"model.layers.39.self_attn.o_proj": [
5120,
6144
],
"model.layers.39.self_attn.q_proj": [
12288,
5120
],
"model.layers.39.self_attn.v_proj": [
1024,
5120
],
"model.layers.4.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.4.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.4.linear_attn.out_proj": [
5120,
6144
],
"model.layers.4.mlp.down_proj": [
5120,
17408
],
"model.layers.4.mlp.gate_proj": [
17408,
5120
],
"model.layers.4.mlp.up_proj": [
17408,
5120
],
"model.layers.40.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.40.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.40.linear_attn.out_proj": [
5120,
6144
],
"model.layers.40.mlp.down_proj": [
5120,
17408
],
"model.layers.40.mlp.gate_proj": [
17408,
5120
],
"model.layers.40.mlp.up_proj": [
17408,
5120
],
"model.layers.41.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.41.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.41.linear_attn.out_proj": [
5120,
6144
],
"model.layers.41.mlp.down_proj": [
5120,
17408
],
"model.layers.41.mlp.gate_proj": [
17408,
5120
],
"model.layers.41.mlp.up_proj": [
17408,
5120
],
"model.layers.42.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.42.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.42.linear_attn.out_proj": [
5120,
6144
],
"model.layers.42.mlp.down_proj": [
5120,
17408
],
"model.layers.42.mlp.gate_proj": [
17408,
5120
],
"model.layers.42.mlp.up_proj": [
17408,
5120
],
"model.layers.43.mlp.down_proj": [
5120,
17408
],
"model.layers.43.mlp.gate_proj": [
17408,
5120
],
"model.layers.43.mlp.up_proj": [
17408,
5120
],
"model.layers.43.self_attn.k_proj": [
1024,
5120
],
"model.layers.43.self_attn.o_proj": [
5120,
6144
],
"model.layers.43.self_attn.q_proj": [
12288,
5120
],
"model.layers.43.self_attn.v_proj": [
1024,
5120
],
"model.layers.44.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.44.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.44.linear_attn.out_proj": [
5120,
6144
],
"model.layers.44.mlp.down_proj": [
5120,
17408
],
"model.layers.44.mlp.gate_proj": [
17408,
5120
],
"model.layers.44.mlp.up_proj": [
17408,
5120
],
"model.layers.45.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.45.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.45.linear_attn.out_proj": [
5120,
6144
],
"model.layers.45.mlp.down_proj": [
5120,
17408
],
"model.layers.45.mlp.gate_proj": [
17408,
5120
],
"model.layers.45.mlp.up_proj": [
17408,
5120
],
"model.layers.46.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.46.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.46.linear_attn.out_proj": [
5120,
6144
],
"model.layers.46.mlp.down_proj": [
5120,
17408
],
"model.layers.46.mlp.gate_proj": [
17408,
5120
],
"model.layers.46.mlp.up_proj": [
17408,
5120
],
"model.layers.47.mlp.down_proj": [
5120,
17408
],
"model.layers.47.mlp.gate_proj": [
17408,
5120
],
"model.layers.47.mlp.up_proj": [
17408,
5120
],
"model.layers.47.self_attn.k_proj": [
1024,
5120
],
"model.layers.47.self_attn.o_proj": [
5120,
6144
],
"model.layers.47.self_attn.q_proj": [
12288,
5120
],
"model.layers.47.self_attn.v_proj": [
1024,
5120
],
"model.layers.48.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.48.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.48.linear_attn.out_proj": [
5120,
6144
],
"model.layers.48.mlp.down_proj": [
5120,
17408
],
"model.layers.48.mlp.gate_proj": [
17408,
5120
],
"model.layers.48.mlp.up_proj": [
17408,
5120
],
"model.layers.49.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.49.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.49.linear_attn.out_proj": [
5120,
6144
],
"model.layers.49.mlp.down_proj": [
5120,
17408
],
"model.layers.49.mlp.gate_proj": [
17408,
5120
],
"model.layers.49.mlp.up_proj": [
17408,
5120
],
"model.layers.5.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.5.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.5.linear_attn.out_proj": [
5120,
6144
],
"model.layers.5.mlp.down_proj": [
5120,
17408
],
"model.layers.5.mlp.gate_proj": [
17408,
5120
],
"model.layers.5.mlp.up_proj": [
17408,
5120
],
"model.layers.50.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.50.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.50.linear_attn.out_proj": [
5120,
6144
],
"model.layers.50.mlp.down_proj": [
5120,
17408
],
"model.layers.50.mlp.gate_proj": [
17408,
5120
],
"model.layers.50.mlp.up_proj": [
17408,
5120
],
"model.layers.51.mlp.down_proj": [
5120,
17408
],
"model.layers.51.mlp.gate_proj": [
17408,
5120
],
"model.layers.51.mlp.up_proj": [
17408,
5120
],
"model.layers.51.self_attn.k_proj": [
1024,
5120
],
"model.layers.51.self_attn.o_proj": [
5120,
6144
],
"model.layers.51.self_attn.q_proj": [
12288,
5120
],
"model.layers.51.self_attn.v_proj": [
1024,
5120
],
"model.layers.52.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.52.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.52.linear_attn.out_proj": [
5120,
6144
],
"model.layers.52.mlp.down_proj": [
5120,
17408
],
"model.layers.52.mlp.gate_proj": [
17408,
5120
],
"model.layers.52.mlp.up_proj": [
17408,
5120
],
"model.layers.53.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.53.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.53.linear_attn.out_proj": [
5120,
6144
],
"model.layers.53.mlp.down_proj": [
5120,
17408
],
"model.layers.53.mlp.gate_proj": [
17408,
5120
],
"model.layers.53.mlp.up_proj": [
17408,
5120
],
"model.layers.54.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.54.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.54.linear_attn.out_proj": [
5120,
6144
],
"model.layers.54.mlp.down_proj": [
5120,
17408
],
"model.layers.54.mlp.gate_proj": [
17408,
5120
],
"model.layers.54.mlp.up_proj": [
17408,
5120
],
"model.layers.55.mlp.down_proj": [
5120,
17408
],
"model.layers.55.mlp.gate_proj": [
17408,
5120
],
"model.layers.55.mlp.up_proj": [
17408,
5120
],
"model.layers.55.self_attn.k_proj": [
1024,
5120
],
"model.layers.55.self_attn.o_proj": [
5120,
6144
],
"model.layers.55.self_attn.q_proj": [
12288,
5120
],
"model.layers.55.self_attn.v_proj": [
1024,
5120
],
"model.layers.56.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.56.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.56.linear_attn.out_proj": [
5120,
6144
],
"model.layers.56.mlp.down_proj": [
5120,
17408
],
"model.layers.56.mlp.gate_proj": [
17408,
5120
],
"model.layers.56.mlp.up_proj": [
17408,
5120
],
"model.layers.57.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.57.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.57.linear_attn.out_proj": [
5120,
6144
],
"model.layers.57.mlp.down_proj": [
5120,
17408
],
"model.layers.57.mlp.gate_proj": [
17408,
5120
],
"model.layers.57.mlp.up_proj": [
17408,
5120
],
"model.layers.58.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.58.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.58.linear_attn.out_proj": [
5120,
6144
],
"model.layers.58.mlp.down_proj": [
5120,
17408
],
"model.layers.58.mlp.gate_proj": [
17408,
5120
],
"model.layers.58.mlp.up_proj": [
17408,
5120
],
"model.layers.59.mlp.down_proj": [
5120,
17408
],
"model.layers.59.mlp.gate_proj": [
17408,
5120
],
"model.layers.59.mlp.up_proj": [
17408,
5120
],
"model.layers.59.self_attn.k_proj": [
1024,
5120
],
"model.layers.59.self_attn.o_proj": [
5120,
6144
],
"model.layers.59.self_attn.q_proj": [
12288,
5120
],
"model.layers.59.self_attn.v_proj": [
1024,
5120
],
"model.layers.6.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.6.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.6.linear_attn.out_proj": [
5120,
6144
],
"model.layers.6.mlp.down_proj": [
5120,
17408
],
"model.layers.6.mlp.gate_proj": [
17408,
5120
],
"model.layers.6.mlp.up_proj": [
17408,
5120
],
"model.layers.60.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.60.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.60.linear_attn.out_proj": [
5120,
6144
],
"model.layers.60.mlp.down_proj": [
5120,
17408
],
"model.layers.60.mlp.gate_proj": [
17408,
5120
],
"model.layers.60.mlp.up_proj": [
17408,
5120
],
"model.layers.61.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.61.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.61.linear_attn.out_proj": [
5120,
6144
],
"model.layers.61.mlp.down_proj": [
5120,
17408
],
"model.layers.61.mlp.gate_proj": [
17408,
5120
],
"model.layers.61.mlp.up_proj": [
17408,
5120
],
"model.layers.62.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.62.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.62.linear_attn.out_proj": [
5120,
6144
],
"model.layers.62.mlp.down_proj": [
5120,
17408
],
"model.layers.62.mlp.gate_proj": [
17408,
5120
],
"model.layers.62.mlp.up_proj": [
17408,
5120
],
"model.layers.63.mlp.down_proj": [
5120,
17408
],
"model.layers.63.mlp.gate_proj": [
17408,
5120
],
"model.layers.63.mlp.up_proj": [
17408,
5120
],
"model.layers.63.self_attn.k_proj": [
1024,
5120
],
"model.layers.63.self_attn.o_proj": [
5120,
6144
],
"model.layers.63.self_attn.q_proj": [
12288,
5120
],
"model.layers.63.self_attn.v_proj": [
1024,
5120
],
"model.layers.7.mlp.down_proj": [
5120,
17408
],
"model.layers.7.mlp.gate_proj": [
17408,
5120
],
"model.layers.7.mlp.up_proj": [
17408,
5120
],
"model.layers.7.self_attn.k_proj": [
1024,
5120
],
"model.layers.7.self_attn.o_proj": [
5120,
6144
],
"model.layers.7.self_attn.q_proj": [
12288,
5120
],
"model.layers.7.self_attn.v_proj": [
1024,
5120
],
"model.layers.8.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.8.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.8.linear_attn.out_proj": [
5120,
6144
],
"model.layers.8.mlp.down_proj": [
5120,
17408
],
"model.layers.8.mlp.gate_proj": [
17408,
5120
],
"model.layers.8.mlp.up_proj": [
17408,
5120
],
"model.layers.9.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.9.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.9.linear_attn.out_proj": [
5120,
6144
],
"model.layers.9.mlp.down_proj": [
5120,
17408
],
"model.layers.9.mlp.gate_proj": [
17408,
5120
],
"model.layers.9.mlp.up_proj": [
17408,
5120
]
}
}
{
"linears": {
"lm_head": [
248320,
5120
],
"model.embed_tokens": [
248320,
5120
],
"model.layers.0.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.0.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.0.linear_attn.out_proj": [
5120,
6144
],
"model.layers.0.mlp.down_proj": [
5120,
17408
],
"model.layers.0.mlp.gate_proj": [
17408,
5120
],
"model.layers.0.mlp.up_proj": [
17408,
5120
],
"model.layers.1.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.1.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.1.linear_attn.out_proj": [
5120,
6144
],
"model.layers.1.mlp.down_proj": [
5120,
17408
],
"model.layers.1.mlp.gate_proj": [
17408,
5120
],
"model.layers.1.mlp.up_proj": [
17408,
5120
],
"model.layers.10.linear_attn.in_proj_qkv": [
10240,
5120
],
"model.layers.10.linear_attn.in_proj_z": [
6144,
5120
],
"model.layers.10.linear_attn.out_proj": [
5120,
6144
],
"model.layers.10.mlp.down_proj": [
5120,
17408
],
"model.layers.10.mlp.gate_proj": [
17408,
5120
],
"model.layers.10.mlp.up_proj": [
17408,
5120
],
"model.layers.11.mlp.down_proj": [
5120,
17408
],
"model.layers.11.mlp.gate_proj": [
17408,
5120
],
"model.layers.11.mlp.up_proj": [
17408,
5120
],
"model.layers.11.self_attn.k_proj": [
1024,
5120
],
"model.layers.11.self_attn.o_proj": [
5120,