Instructions to use ridger/MMfreeLM-2.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ridger/MMfreeLM-2.7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ridger/MMfreeLM-2.7B")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ridger/MMfreeLM-2.7B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ridger/MMfreeLM-2.7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ridger/MMfreeLM-2.7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ridger/MMfreeLM-2.7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ridger/MMfreeLM-2.7B
- SGLang
How to use ridger/MMfreeLM-2.7B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ridger/MMfreeLM-2.7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ridger/MMfreeLM-2.7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ridger/MMfreeLM-2.7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ridger/MMfreeLM-2.7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ridger/MMfreeLM-2.7B with Docker Model Runner:
docker model run hf.co/ridger/MMfreeLM-2.7B
"MMfreeLM-2.7B: hgrn_bit architecture not recognized by transformers (after source install)"
We're currently experiencing a compatibility issue when trying to load the ridger/MMfreeLM-2.7B model. The primary error is ValueError: The checkpoint you are trying to load has model type 'hgrn_bit' but Transformers does not recognize this architecture.
We've attempted several troubleshooting steps, including:
Upgrading transformers via pip install --upgrade transformers.
Installing transformers directly from the main branch of its GitHub repository (pip install git+https://github.com/huggingface/transformers.git).
Performing a complete reinstallation of all dependencies, including mmfreelm.
Despite these efforts, the hgrn_bit architecture remains unrecognized by the transformers library, preventing the model from loading correctly. We're seeking guidance on potential solutions, such as specific transformers versions required, any custom installation steps, or known workarounds for this architecture.
i certainly got it. The Trick is using the old dependencies that were used to compile the LLM. it worked but after a hustle


