| { |
| "_name_or_path": "/home/titan-6/.cache/huggingface/hub/models--TitanML--tiny-mixtral/snapshots/f27916c59dac2dbd8ee7a8fc0355dba2e85e3956", |
| "architectures": [ |
| "MixtralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 3584, |
| "max_position_embeddings": 131072, |
| "model_type": "mixtral", |
| "num_attention_heads": 32, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 8, |
| "num_local_experts": 8, |
| "output_router_logits": false, |
| "quantization_config": { |
| "bits": 4, |
| "group_size": 128, |
| "modules_to_not_convert": [ |
| "gate", |
| "lm_head" |
| ], |
| "quant_method": "awq", |
| "version": "gemm", |
| "zero_point": true |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 1000000.0, |
| "router_aux_loss_coef": 0.001, |
| "router_jitter_noise": 0.0, |
| "sliding_window": 4096, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.41.1", |
| "use_cache": false, |
| "vocab_size": 32000 |
| } |
|
|