File size: 1,224 Bytes
87f960a 0f53cb7 87f960a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
{
"_name_or_path": "HuatuoGPT2-34B-4bits",
"architectures": [
"YiForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_yi.YiConfig",
"AutoModel": "modeling_yi.YiModel",
"AutoModelForCausalLM": "modeling_yi.YiForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 7168,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 4096,
"model_type": "Yi",
"num_attention_heads": 56,
"num_hidden_layers": 60,
"num_key_value_heads": 8,
"pad_token_id": 0,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": "model.layers",
"damp_percent": 0.1,
"desc_act": false,
"disable_exllama": true,
"group_size": 128,
"model_seqlen": 4096,
"module_name_preceding_first_block": [
"model.embed_tokens"
],
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 5000000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.33.1",
"use_cache": true,
"vocab_size": 64000
}
|