| { | |
| "_name_or_path": "/srv/hf-cache/hub/models--CohereForAI--aya-expanse-8b/snapshots/d10159f8405826732641ce11c6892459d447d48c", | |
| "architectures": [ | |
| "CohereForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 5, | |
| "eos_token_id": 255001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "layer_norm_eps": 1e-05, | |
| "logit_scale": 0.125, | |
| "max_position_embeddings": 8192, | |
| "model_type": "cohere", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": null, | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.47.1", | |
| "use_cache": false, | |
| "use_qk_norm": false, | |
| "vocab_size": 256000 | |
| } | |