| { | |
| "_name_or_path": "/workspace/process/causallm_8x7b-moe-test-not-mixtral/source", | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "num_local_experts": 8, | |
| "output_router_logits": false, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": null, | |
| "cache_block_outputs": true, | |
| "damp_percent": 0.1, | |
| "desc_act": true, | |
| "exllama_config": { | |
| "version": 1 | |
| }, | |
| "group_size": -1, | |
| "max_input_length": null, | |
| "model_seqlen": null, | |
| "module_name_preceding_first_block": null, | |
| "modules_in_block_to_quantize": [ | |
| [ | |
| "self_attn.k_proj", | |
| "self_attn.v_proj", | |
| "self_attn.q_proj" | |
| ], | |
| [ | |
| "self_attn.o_proj" | |
| ], | |
| [ | |
| "block_sparse_moe.experts.0.w1", | |
| "block_sparse_moe.experts.1.w1", | |
| "block_sparse_moe.experts.2.w1", | |
| "block_sparse_moe.experts.3.w1", | |
| "block_sparse_moe.experts.4.w1", | |
| "block_sparse_moe.experts.5.w1", | |
| "block_sparse_moe.experts.6.w1", | |
| "block_sparse_moe.experts.7.w1", | |
| "block_sparse_moe.experts.0.w3", | |
| "block_sparse_moe.experts.1.w3", | |
| "block_sparse_moe.experts.2.w3", | |
| "block_sparse_moe.experts.3.w3", | |
| "block_sparse_moe.experts.4.w3", | |
| "block_sparse_moe.experts.5.w3", | |
| "block_sparse_moe.experts.6.w3", | |
| "block_sparse_moe.experts.7.w3" | |
| ], | |
| [ | |
| "block_sparse_moe.experts.0.w2", | |
| "block_sparse_moe.experts.1.w2", | |
| "block_sparse_moe.experts.2.w2", | |
| "block_sparse_moe.experts.3.w2", | |
| "block_sparse_moe.experts.4.w2", | |
| "block_sparse_moe.experts.5.w2", | |
| "block_sparse_moe.experts.6.w2", | |
| "block_sparse_moe.experts.7.w2" | |
| ] | |
| ], | |
| "pad_token_id": null, | |
| "quant_method": "gptq", | |
| "sym": true, | |
| "tokenizer": null, | |
| "true_sequential": true, | |
| "use_cuda_fp16": false, | |
| "use_exllama": true | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "sliding_window": 8192, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 151936 | |
| } |