| { | |
| "_name_or_path": "/home/sadkins/.cache/huggingface/hub/models--mistralai--Mixtral-8x7B-Instruct-v0.1/snapshots/67c3bf6b0aa8b6670f892629331d314f9af0b522", | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "compression_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": 1.536450042423991, | |
| "ignore": [ | |
| "model.layers.0.block_sparse_moe.gate", | |
| "model.layers.1.block_sparse_moe.gate", | |
| "model.layers.2.block_sparse_moe.gate", | |
| "model.layers.3.block_sparse_moe.gate", | |
| "model.layers.4.block_sparse_moe.gate", | |
| "model.layers.5.block_sparse_moe.gate", | |
| "model.layers.6.block_sparse_moe.gate", | |
| "model.layers.7.block_sparse_moe.gate", | |
| "model.layers.8.block_sparse_moe.gate", | |
| "model.layers.9.block_sparse_moe.gate", | |
| "model.layers.10.block_sparse_moe.gate", | |
| "model.layers.11.block_sparse_moe.gate", | |
| "model.layers.12.block_sparse_moe.gate", | |
| "model.layers.13.block_sparse_moe.gate", | |
| "model.layers.14.block_sparse_moe.gate", | |
| "model.layers.15.block_sparse_moe.gate", | |
| "model.layers.16.block_sparse_moe.gate", | |
| "model.layers.17.block_sparse_moe.gate", | |
| "model.layers.18.block_sparse_moe.gate", | |
| "model.layers.19.block_sparse_moe.gate", | |
| "model.layers.20.block_sparse_moe.gate", | |
| "model.layers.21.block_sparse_moe.gate", | |
| "model.layers.22.block_sparse_moe.gate", | |
| "model.layers.23.block_sparse_moe.gate", | |
| "model.layers.24.block_sparse_moe.gate", | |
| "model.layers.25.block_sparse_moe.gate", | |
| "model.layers.26.block_sparse_moe.gate", | |
| "model.layers.27.block_sparse_moe.gate", | |
| "model.layers.28.block_sparse_moe.gate", | |
| "model.layers.29.block_sparse_moe.gate", | |
| "model.layers.30.block_sparse_moe.gate", | |
| "model.layers.31.block_sparse_moe.gate", | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "frozen" | |
| }, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 8, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "router_aux_loss_coef": 0.02, | |
| "router_jitter_noise": 0.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.43.4", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } |