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
- 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
Create generation_config.json
Browse files- generation_config.json +104 -0
generation_config.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.40.0",
|
| 7 |
+
"model_type": "helion-osc",
|
| 8 |
+
"do_sample": true,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"top_k": 50,
|
| 12 |
+
"repetition_penalty": 1.05,
|
| 13 |
+
"length_penalty": 1.0,
|
| 14 |
+
"no_repeat_ngram_size": 3,
|
| 15 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 16 |
+
"num_beams": 1,
|
| 17 |
+
"num_beam_groups": 1,
|
| 18 |
+
"diversity_penalty": 0.0,
|
| 19 |
+
"early_stopping": false,
|
| 20 |
+
"max_length": 16384,
|
| 21 |
+
"max_new_tokens": null,
|
| 22 |
+
"min_length": 0,
|
| 23 |
+
"min_new_tokens": null,
|
| 24 |
+
"exponential_decay_length_penalty": null,
|
| 25 |
+
"remove_invalid_values": false,
|
| 26 |
+
"output_scores": false,
|
| 27 |
+
"output_attentions": false,
|
| 28 |
+
"output_hidden_states": false,
|
| 29 |
+
"return_dict_in_generate": false,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"suppress_tokens": null,
|
| 33 |
+
"begin_suppress_tokens": null,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"task_profiles": {
|
| 36 |
+
"code_generation_creative": {
|
| 37 |
+
"temperature": 0.8,
|
| 38 |
+
"top_p": 0.95,
|
| 39 |
+
"top_k": 60,
|
| 40 |
+
"repetition_penalty": 1.08,
|
| 41 |
+
"max_new_tokens": 4096,
|
| 42 |
+
"description": "Creative code generation with diverse solutions"
|
| 43 |
+
},
|
| 44 |
+
"code_generation_precise": {
|
| 45 |
+
"temperature": 0.3,
|
| 46 |
+
"top_p": 0.85,
|
| 47 |
+
"top_k": 40,
|
| 48 |
+
"repetition_penalty": 1.02,
|
| 49 |
+
"max_new_tokens": 4096,
|
| 50 |
+
"do_sample": false,
|
| 51 |
+
"description": "Precise, deterministic code generation"
|
| 52 |
+
},
|
| 53 |
+
"mathematical_proof": {
|
| 54 |
+
"temperature": 0.2,
|
| 55 |
+
"top_p": 0.8,
|
| 56 |
+
"top_k": 30,
|
| 57 |
+
"repetition_penalty": 1.0,
|
| 58 |
+
"max_new_tokens": 3072,
|
| 59 |
+
"do_sample": false,
|
| 60 |
+
"description": "Rigorous mathematical proofs and derivations"
|
| 61 |
+
},
|
| 62 |
+
"algorithm_optimization": {
|
| 63 |
+
"temperature": 0.5,
|
| 64 |
+
"top_p": 0.92,
|
| 65 |
+
"top_k": 50,
|
| 66 |
+
"repetition_penalty": 1.1,
|
| 67 |
+
"max_new_tokens": 3072,
|
| 68 |
+
"description": "Algorithm design with optimization focus"
|
| 69 |
+
},
|
| 70 |
+
"code_explanation": {
|
| 71 |
+
"temperature": 0.6,
|
| 72 |
+
"top_p": 0.9,
|
| 73 |
+
"top_k": 45,
|
| 74 |
+
"repetition_penalty": 1.05,
|
| 75 |
+
"max_new_tokens": 2048,
|
| 76 |
+
"description": "Detailed code explanations and documentation"
|
| 77 |
+
},
|
| 78 |
+
"debugging_analysis": {
|
| 79 |
+
"temperature": 0.4,
|
| 80 |
+
"top_p": 0.88,
|
| 81 |
+
"top_k": 40,
|
| 82 |
+
"repetition_penalty": 1.0,
|
| 83 |
+
"max_new_tokens": 2048,
|
| 84 |
+
"do_sample": false,
|
| 85 |
+
"description": "Systematic debugging and error analysis"
|
| 86 |
+
},
|
| 87 |
+
"competitive_programming": {
|
| 88 |
+
"temperature": 0.65,
|
| 89 |
+
"top_p": 0.93,
|
| 90 |
+
"top_k": 55,
|
| 91 |
+
"repetition_penalty": 1.12,
|
| 92 |
+
"max_new_tokens": 2048,
|
| 93 |
+
"description": "Competitive programming solutions"
|
| 94 |
+
},
|
| 95 |
+
"system_design": {
|
| 96 |
+
"temperature": 0.7,
|
| 97 |
+
"top_p": 0.94,
|
| 98 |
+
"top_k": 55,
|
| 99 |
+
"repetition_penalty": 1.06,
|
| 100 |
+
"max_new_tokens": 4096,
|
| 101 |
+
"description": "System architecture and design patterns"
|
| 102 |
+
}
|
| 103 |
+
}
|
| 104 |
+
}
|