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)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("codelion/dhara-70m", trust_remote_code=True, device_map="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
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -155,10 +155,10 @@ Canon layers are causal depthwise convolutions that provide local context mixing
|
|
| 155 |
If you use this model, please cite our blog post:
|
| 156 |
|
| 157 |
```bibtex
|
| 158 |
-
@article{
|
| 159 |
title={Optimal Model Architecture},
|
| 160 |
author={CodeLion},
|
| 161 |
-
year={
|
| 162 |
journal={Hugging Face Blog},
|
| 163 |
url={https://huggingface.co/blog/codelion/optimal-model-architecture}
|
| 164 |
}
|
|
|
|
| 155 |
If you use this model, please cite our blog post:
|
| 156 |
|
| 157 |
```bibtex
|
| 158 |
+
@article{dhara2025,
|
| 159 |
title={Optimal Model Architecture},
|
| 160 |
author={CodeLion},
|
| 161 |
+
year={2025},
|
| 162 |
journal={Hugging Face Blog},
|
| 163 |
url={https://huggingface.co/blog/codelion/optimal-model-architecture}
|
| 164 |
}
|