| { |
| "_name_or_path": "/weka2/home-duyphung/stablelm2-ckpts/stablecode-3b-sft-1003-v1-neft-tune-safe-name", |
| "architectures": [ |
| "StableLmForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "eos_token_id": 0, |
| "hidden_act": "silu", |
| "hidden_dropout": 0.0, |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 6912, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 16384, |
| "model_type": "stablelm", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "partial_rotary_factor": 0.25, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.38.2", |
| "use_cache": false, |
| "use_qkv_bias": false, |
| "vocab_size": 50304 |
| } |
|
|