| { |
| "_name_or_path": "./llama-7b-hf", |
| "architectures": ["LlamaForCausalLM"], |
| "bos_token_id": 0, |
| "eos_token_id": 1, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "max_sequence_length": 2048, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "pad_token_id": -1, |
| "rms_norm_eps": 1e-6, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.28.0.dev0", |
| "use_cache": true, |
| "vocab_size": 32001, |
| "quantization_config": { |
| "bits": 4, |
| "group_size": 128, |
| "damp_percent": 0.01, |
| "desc_act": false, |
| "sym": true, |
| "true_sequential": true, |
| "model_name_or_path": null, |
| "model_file_base_name": "model", |
| "quant_method": "gptq" |
| } |
| } |
|
|
