|
{ |
|
"_name_or_path": "/workspace/process/fblgit_una-thebeagle-7b-v1/source", |
|
"architectures": [ |
|
"MistralForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"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, |
|
"pad_token_id": 0, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 10000.0, |
|
"sliding_window": 4096, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.36.2", |
|
"use_cache": true, |
|
"vocab_size": 32000, |
|
"quantization_config": { |
|
"bits": 4, |
|
"group_size": 128, |
|
"damp_percent": 0.1, |
|
"desc_act": true, |
|
"static_groups": false, |
|
"sym": true, |
|
"true_sequential": true, |
|
"model_name_or_path": null, |
|
"model_file_base_name": "model", |
|
"quant_method": "gptq", |
|
"modules_in_block_to_quantize": [ |
|
[ |
|
"self_attn.k_proj", |
|
"self_attn.v_proj", |
|
"self_attn.q_proj" |
|
], |
|
[ |
|
"self_attn.o_proj" |
|
], |
|
[ |
|
"mlp.up_proj", |
|
"mlp.gate_proj" |
|
], |
|
[ |
|
"mlp.down_proj" |
|
] |
|
] |
|
} |
|
} |