Text Generation
Transformers
Safetensors
English
dhara
feature-extraction
diffusion
language-model
causal-lm
custom_code
Eval Results (legacy)
Instructions to use codelion/dhara-70m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codelion/dhara-70m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="codelion/dhara-70m", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("codelion/dhara-70m", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use codelion/dhara-70m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "codelion/dhara-70m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codelion/dhara-70m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/codelion/dhara-70m
- SGLang
How to use codelion/dhara-70m 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 "codelion/dhara-70m" \ --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": "codelion/dhara-70m", "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 "codelion/dhara-70m" \ --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": "codelion/dhara-70m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use codelion/dhara-70m with Docker Model Runner:
docker model run hf.co/codelion/dhara-70m
1024 in max_position_embeddings
#2
by khtsly - opened
Good catch! the actual context length is 1024 tokens. The README incorrectly stated 2048, I've updated it to reflect the correct value. Thanks for flagging this!
codelion changed discussion status to closed

