Haoxiang-Wang's picture
Upload MistralForAttributePrediction
12f4861 verified
raw
history blame
No virus
1.19 kB
{
"_name_or_path": "/data-3/common/reward-cond-llm/logs/reward-model-mistral-7b_helpsteer+ultrafeedback-v2.0_instruct-v2_lr5e-6_bs256_reg3e-3/checkpoint-1092",
"architectures": [
"MistralForAttributePrediction"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9"
},
"initializer_range": 0.02,
"intermediate_size": 14336,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9
},
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.39.3",
"use_cache": true,
"vocab_size": 32000
}