sharpenb's picture
Upload folder using huggingface_hub (#3)
4ed3b49 verified
raw
history blame
1.39 kB
{
"_name_or_path": "/tmp/tmptoahj57j",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoModel": "GritLM/GritLM-7B--modeling_gritlm7b.MistralModel",
"AutoModelForCausalLM": "modeling_gritlm7b.MistralForCausalLM",
"AutoModelForSequenceClassification": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForSequenceClassification"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 14336,
"label2id": {
"LABEL_0": 0
},
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"quantization_config": {
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": [
"lm_head"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.1",
"use_cache": true,
"vocab_size": 32000
}