| { | |
| "_name_or_path": "/workspace/process/berkeley-nest_starling-lm-7b-alpha/source", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.35.2", | |
| "use_cache": true, | |
| "vocab_size": 32002, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "damp_percent": 0.1, | |
| "desc_act": true, | |
| "sym": true, | |
| "true_sequential": true, | |
| "model_name_or_path": null, | |
| "model_file_base_name": "model", | |
| "quant_method": "gptq" | |
| } | |
| } |