Text Generation
Transformers
Safetensors
English
code
helion-osc
mathematics
reasoning
algorithm
causal-lm
conversational
bitsandbytes
Instructions to use DeepXR/Helion-OSC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DeepXR/Helion-OSC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DeepXR/Helion-OSC") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DeepXR/Helion-OSC", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DeepXR/Helion-OSC with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DeepXR/Helion-OSC" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DeepXR/Helion-OSC", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DeepXR/Helion-OSC
- SGLang
How to use DeepXR/Helion-OSC 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 "DeepXR/Helion-OSC" \ --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": "DeepXR/Helion-OSC", "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 "DeepXR/Helion-OSC" \ --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": "DeepXR/Helion-OSC", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DeepXR/Helion-OSC with Docker Model Runner:
docker model run hf.co/DeepXR/Helion-OSC
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "pad_token_id": 0, | |
| "transformers_version": "4.40.0", | |
| "model_type": "helion-osc", | |
| "do_sample": true, | |
| "temperature": 0.7, | |
| "top_p": 0.95, | |
| "top_k": 50, | |
| "repetition_penalty": 1.05, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 3, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "early_stopping": false, | |
| "max_length": 16384, | |
| "max_new_tokens": null, | |
| "min_length": 0, | |
| "min_new_tokens": null, | |
| "exponential_decay_length_penalty": null, | |
| "remove_invalid_values": false, | |
| "output_scores": false, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "use_cache": true, | |
| "task_profiles": { | |
| "code_generation_creative": { | |
| "temperature": 0.8, | |
| "top_p": 0.95, | |
| "top_k": 60, | |
| "repetition_penalty": 1.08, | |
| "max_new_tokens": 4096, | |
| "description": "Creative code generation with diverse solutions" | |
| }, | |
| "code_generation_precise": { | |
| "temperature": 0.3, | |
| "top_p": 0.85, | |
| "top_k": 40, | |
| "repetition_penalty": 1.02, | |
| "max_new_tokens": 4096, | |
| "do_sample": false, | |
| "description": "Precise, deterministic code generation" | |
| }, | |
| "mathematical_proof": { | |
| "temperature": 0.2, | |
| "top_p": 0.8, | |
| "top_k": 30, | |
| "repetition_penalty": 1.0, | |
| "max_new_tokens": 3072, | |
| "do_sample": false, | |
| "description": "Rigorous mathematical proofs and derivations" | |
| }, | |
| "algorithm_optimization": { | |
| "temperature": 0.5, | |
| "top_p": 0.92, | |
| "top_k": 50, | |
| "repetition_penalty": 1.1, | |
| "max_new_tokens": 3072, | |
| "description": "Algorithm design with optimization focus" | |
| }, | |
| "code_explanation": { | |
| "temperature": 0.6, | |
| "top_p": 0.9, | |
| "top_k": 45, | |
| "repetition_penalty": 1.05, | |
| "max_new_tokens": 2048, | |
| "description": "Detailed code explanations and documentation" | |
| }, | |
| "debugging_analysis": { | |
| "temperature": 0.4, | |
| "top_p": 0.88, | |
| "top_k": 40, | |
| "repetition_penalty": 1.0, | |
| "max_new_tokens": 2048, | |
| "do_sample": false, | |
| "description": "Systematic debugging and error analysis" | |
| }, | |
| "competitive_programming": { | |
| "temperature": 0.65, | |
| "top_p": 0.93, | |
| "top_k": 55, | |
| "repetition_penalty": 1.12, | |
| "max_new_tokens": 2048, | |
| "description": "Competitive programming solutions" | |
| }, | |
| "system_design": { | |
| "temperature": 0.7, | |
| "top_p": 0.94, | |
| "top_k": 55, | |
| "repetition_penalty": 1.06, | |
| "max_new_tokens": 4096, | |
| "description": "System architecture and design patterns" | |
| } | |
| } | |
| } |