|
{ |
|
"_name_or_path": "UCLAML/mistral-7b-expert-iteration-iter3", |
|
"architectures": [ |
|
"MistralForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 32768, |
|
"model_type": "mistral", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"quantization_config": { |
|
"batch_size": 1, |
|
"bits": 8, |
|
"block_name_to_quantize": null, |
|
"cache_block_outputs": true, |
|
"damp_percent": 0.1, |
|
"dataset": "c4", |
|
"desc_act": false, |
|
"exllama_config": { |
|
"version": 1 |
|
}, |
|
"group_size": 128, |
|
"max_input_length": null, |
|
"model_seqlen": null, |
|
"module_name_preceding_first_block": null, |
|
"modules_in_block_to_quantize": null, |
|
"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-05, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": null, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.43.4", |
|
"use_cache": true, |
|
"vocab_size": 32000 |
|
} |
|
|