Text Generation
GGUF
Safetensors
English
deepseek2
llama.cpp
mixture-of-experts
multi-head-latent-attention
iq4_nl
mark-ai
systems-engineering
custom_code
conversational
Instructions to use miceworks/Mark-SLM-V3-150M 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 miceworks/Mark-SLM-V3-150M 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 miceworks/Mark-SLM-V3-150M:IQ4_NL # Run inference directly in the terminal: llama cli -hf miceworks/Mark-SLM-V3-150M:IQ4_NL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf miceworks/Mark-SLM-V3-150M:IQ4_NL # Run inference directly in the terminal: llama cli -hf miceworks/Mark-SLM-V3-150M:IQ4_NL
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 miceworks/Mark-SLM-V3-150M:IQ4_NL # Run inference directly in the terminal: ./build/bin/llama cli -hf miceworks/Mark-SLM-V3-150M:IQ4_NL
Use Docker
docker model run hf.co/miceworks/Mark-SLM-V3-150M:IQ4_NL
- Llama new
- LM Studio
- Jan
- vLLM
How to use miceworks/Mark-SLM-V3-150M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "miceworks/Mark-SLM-V3-150M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "miceworks/Mark-SLM-V3-150M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/miceworks/Mark-SLM-V3-150M:IQ4_NL
- Ollama
How to use miceworks/Mark-SLM-V3-150M with Ollama:
ollama run hf.co/miceworks/Mark-SLM-V3-150M:IQ4_NL
- Unsloth Desktop
- Docker Model Runner
How to use miceworks/Mark-SLM-V3-150M with Docker Model Runner:
docker model run hf.co/miceworks/Mark-SLM-V3-150M:IQ4_NL
- Lemonade
How to use miceworks/Mark-SLM-V3-150M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull miceworks/Mark-SLM-V3-150M:IQ4_NL
Run and chat with the model
lemonade run user.Mark-SLM-V3-150M-IQ4_NL
List all available models
lemonade list
- Atomic Chat
Commit History
10 days ago
-
mark-50 5h 7-way stream artifact: mark_slm_v3_150m_mark50_f16.gguf
Verified signature072332a -
mark-50 5h 7-way stream artifact: mark_slm_v3_150m_mark50_bf16.safetensors
Verified signaturedc68bfc -
Train V2 16-bit artifact: mark_slm_v3_150m_v2_f16.gguf
Verified signatureda8c092 -
Train V2 16-bit artifact: mark_slm_v3_150m_v2_bf16.safetensors
Verified signature0b52aae
11 days ago
-
restore: revert mark_slm_v3_150m_iq4_nl.gguf to verified 16.36 baseline checkpoint
Verified signaturec4c99ad -
restore: revert model.safetensors to verified 16.36 baseline checkpoint
Verified signature01bde69 -
restore: revert modeling_mark_v3.py to verified 16.36 baseline checkpoint
Verified signature376a516 -
restore: revert configuration_mark_v3.py to verified 16.36 baseline checkpoint
Verified signatureae7ebaa -
restore: revert config.json to verified 16.36 baseline checkpoint
Verified signature67e4dea -
revert: remove overfitted test artifact mark_slm_v3_150m_final.pt
Verified signature991d4cb -
revert: remove overfitted test artifact eval_summary.json
Verified signaturebd7b973 -
revert: remove overfitted test artifact leaderboard_eval_results_mark45.json
Verified signature8ab6994 -
[mark-45] Official lm-eval 0-shot results: Intelligence Index 5.19
Verified signature1877088 -
Sync MarkV3 HF AutoModel loader for 12h trained weights (modeling_mark_v3.py)
Verified signatureeb8eb97 -
Sync MarkV3 HF AutoModel loader for 12h trained weights (configuration_mark_v3.py)
Verified signature0cd0552 -
Sync MarkV3 HF AutoModel loader for 12h trained weights (modeling_mark_v3.py)
Verified signature98b94df -
Sync MarkV3 HF AutoModel loader for 12h trained weights (configuration_mark_v3.py)
Verified signature185e8ff -
Sync MarkV3 HF AutoModel loader for 12h trained weights (config.json)
Verified signature771ed82 -
Kaggle 2x T4 mark-44 Complete: OptStep 10727 | Loss 0.0225 | 150M SLM
Verified signature2ceb5e7 -
Kaggle 2x T4 mark-44 Complete: OptStep 10727 | Loss 0.0225 | 150M SLM
Verified signature354fd38 -
Kaggle 2x T4 mark-44 Complete: OptStep 10727 | Loss 0.0225 | 150M SLM
Verified signature51dae72 -
Kaggle 2x T4 mark-44 Complete: OptStep 10727 | Loss 0.0225 | 150M SLM
Verified signaturebe2e4eb -
Periodic 2h Checkpoint: OptStep 9527 | Loss 0.0724
Verified signature866009b
12 days ago
-
Periodic 2h Checkpoint: OptStep 7612 | Loss 0.0564
Verified signature61cf80b -
Periodic 2h Checkpoint: OptStep 5707 | Loss 0.0663
Verified signaturef02f52c -
Periodic 2h Checkpoint: OptStep 3790 | Loss 0.1083
Verified signature93049ff -
Periodic 2h Checkpoint: OptStep 1886 | Loss 0.4004
Verified signature0121ede -
docs: sync test-verified README.md
Verified signaturea708ca2 -
Update verified artifact: gguf_verification_manifest.json
Verified signature5661dcc -
Update verified artifact: config.json
Verified signatured91a55e -
Update verified artifact: README.md
Verified signature864cb35
15 days ago
-
Super-squash branch 'main' using huggingface_hub
a14a820