| { | |
| "_name_or_path": "/home/pikal/Coding/alpacacielo/v2/guanacohermes7b", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "conceptofmind/LLongMA-2-7b--configuration_llama.LlamaConfig", | |
| "AutoModel": "conceptofmind/LLongMA-2-7b--modeling_llama.LlamaModel", | |
| "AutoModelForCausalLM": "conceptofmind/LLongMA-2-7b--modeling_llama.LlamaForCausalLM", | |
| "AutoModelForSequenceClassification": "conceptofmind/LLongMA-2-7b--modeling_llama.LlamaForSequenceClassification" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 8192, | |
| "model_type": "llama", | |
| "ntk_alpha": null, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 0, | |
| "part_ntk_scale": null, | |
| "position_interpolation_scale": 1, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "type": "linear" | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformer_engine": null, | |
| "transformers_version": "4.32.0.dev0", | |
| "use_cache": true, | |
| "use_xpos": false, | |
| "vocab_size": 32000, | |
| "quantization_config": { | |
| "quant_method": "awq", | |
| "zero_point": true, | |
| "group_size": 128, | |
| "bits": 4, | |
| "version": "gemm" | |
| } | |
| } |