| { |
| "model_type": "helion-osc", |
| "architectures": ["HelionOSCForCausalLM"], |
| "vocab_size": 50280, |
| "hidden_size": 4096, |
| "num_hidden_layers": 32, |
| "num_attention_heads": 32, |
| "num_key_value_heads": 8, |
| "intermediate_size": 14336, |
| "hidden_act": "silu", |
| "max_position_embeddings": 8192, |
| "initializer_range": 0.02, |
| "rms_norm_eps": 1e-6, |
| "use_cache": true, |
| "pad_token_id": 0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "tie_word_embeddings": false, |
| "rope_theta": 10000.0, |
| "rope_scaling": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "mlp_bias": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.36.0", |
| "task_specific_params": { |
| "code_generation": { |
| "max_length": 2048, |
| "temperature": 0.7, |
| "top_p": 0.95, |
| "do_sample": true |
| }, |
| "mathematical_reasoning": { |
| "max_length": 1024, |
| "temperature": 0.3, |
| "top_p": 0.9, |
| "do_sample": false |
| } |
| }, |
| "specialization": { |
| "domain": "coding_and_mathematics", |
| "languages_supported": [ |
| "python", |
| "javascript", |
| "typescript", |
| "java", |
| "c++", |
| "rust", |
| "go", |
| "sql" |
| ], |
| "features": [ |
| "code_generation", |
| "code_completion", |
| "bug_detection", |
| "mathematical_reasoning", |
| "algorithm_design", |
| "code_optimization" |
| ] |
| } |
| } |
