Instructions to use reaperdoesntknow/DNA-175M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use reaperdoesntknow/DNA-175M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="reaperdoesntknow/DNA-175M") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/DNA-175M", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use reaperdoesntknow/DNA-175M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "reaperdoesntknow/DNA-175M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "reaperdoesntknow/DNA-175M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/reaperdoesntknow/DNA-175M
- SGLang
How to use reaperdoesntknow/DNA-175M 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 "reaperdoesntknow/DNA-175M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "reaperdoesntknow/DNA-175M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "reaperdoesntknow/DNA-175M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "reaperdoesntknow/DNA-175M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use reaperdoesntknow/DNA-175M with Docker Model Runner:
docker model run hf.co/reaperdoesntknow/DNA-175M
| { | |
| "alpha_init": 1.5, | |
| "architectures": [ | |
| "LiquidForCausalLM" | |
| ], | |
| "attn_drop": 0.1, | |
| "bos_token_id": null, | |
| "chead_kernal_size": 5, | |
| "dim": 256, | |
| "drop": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "feature_heads": 64, | |
| "gnn_n_heads": 4, | |
| "gnn_num_layers": 1, | |
| "hidden": 256, | |
| "learn_alpha": true, | |
| "maha_init": 1.6, | |
| "max_position_embeddings": 512, | |
| "memory_size": 256, | |
| "metric": "maha_diag", | |
| "model_type": "liquid-former", | |
| "n_attn_heads": 8, | |
| "n_delta_windows": 10, | |
| "n_thought_heads": 64, | |
| "num_heads": 32, | |
| "num_layers": 1, | |
| "pad_token_id": 0, | |
| "proj_drop": 0.1, | |
| "router_gate_heads": 32, | |
| "share_kv": true, | |
| "tie_weights": true, | |
| "transformers_version": "4.56.1", | |
| "vocab_size": 151669 | |
| } | |