lrl-modelcloud's picture
Upload folder using huggingface_hub (#1)
0f292c2 verified
raw
history blame
1.38 kB
{
"_name_or_path": "/model/internlm2_5-7b-chat-1m/",
"architectures": [
"InternLM2ForCausalLM"
],
"attn_implementation": "eager",
"auto_map": {
"AutoConfig": "configuration_internlm2.InternLM2Config",
"AutoModel": "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": 262144,
"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": {
"bits": 4,
"checkpoint_format": "gptq",
"damp_percent": 0.01,
"desc_act": true,
"group_size": 128,
"lm_head": false,
"meta": {
"quantizer": "gptqmodel:0.9.5"
},
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 2.5,
"type": "dynamic"
},
"rope_theta": 50000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.0.dev0",
"use_cache": true,
"vocab_size": 92544
}