myownskyW7's picture
init internlm-xcomposer-vl-7b
5985c08
raw
history blame
1.31 kB
{
"_name_or_path": "performance",
"architectures": [
"InternLMXComposerForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_InternLM_XComposer.InternLMXComposerConfig",
"AutoModel": "modeling_InternLM_XComposer.InternLMXComposerForCausalLM",
"AutoModelForCausalLM": "modeling_InternLM_XComposer.InternLMXComposerForCausalLM"
},
"bias": true,
"bos_token_id": 1,
"device": "cuda",
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"intern_converted_llm": true,
"internlm_lora": {
"freeze": false,
"learn_param": [
"q",
"v",
"ffn"
],
"lora_alpha": 256,
"lora_dropout": 0.05,
"lora_r": 256
},
"kqvo_bias": true,
"lora_cfg": {
"freeze": false,
"learn_param": [
"q",
"v",
"ffn"
],
"lora_alpha": 256,
"lora_dropout": 0.05,
"lora_r": 256
},
"max_position_embeddings": 2048,
"model_type": "InternLMXComposer",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_quant": 32,
"num_query_token": 64,
"pad_token_id": -1,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"use_cache": true,
"vocab_size": 103170
}