sharpenb's picture
Upload folder using huggingface_hub (#1)
642ebc3 verified
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelso25djaing7mlqhfy",
"architectures": [
"InternLM2ForCausalLM"
],
"attn_implementation": "eager",
"auto_map": {
"AutoConfig": "configuration_internlm2.InternLM2Config",
"AutoModel": "internlm/internlm2-math-7b--modeling_internlm2.InternLM2ForCausalLM",
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
},
"bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "internlm2",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 2,
"pretraining_tp": 1,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"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_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": true,
"vocab_size": 92544
}