kuotient's picture
Duplicate from allganize/Seagull-13b-v0.6-AWQ
c64335a verified
{
"_name_or_path": "/workspace/hf_cache/hub/models--kuotient--Seagull-13b-v0.6/snapshots/7f1561202170a23226a1a8ce5df8e7c34ef628e4",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 46336,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 2,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.2",
"use_cache": false,
"vocab_size": 46338
}