File size: 1,397 Bytes
46a008b |
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 |
{
"_name_or_path": "/tmp/tmp4nq0y751",
"_remove_final_layer_norm": false,
"activation_dropout": 0.0,
"activation_function": "relu",
"antemplate": "[Genre: <|>]",
"architectures": [
"OPTForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 2,
"do_layer_norm_before": true,
"dropout": 0.1,
"enable_bias": true,
"eos_token_id": 2,
"ffn_dim": 16384,
"hidden_size": 4096,
"init_std": 0.02,
"layer_norm_elementwise_affine": true,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "opt",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 1,
"prefix": "</s>",
"quantization_config": {
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": true,
"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": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"torch_dtype": "float16",
"transformers_version": "4.37.1",
"use_cache": false,
"vocab_size": 50265,
"welcome": "\n\nYou are currently running the model `OPT-6.7B-Nerybus-Mix`\n\nThis is an experimental model containing a parameter-wise 50/50 blend (weighted average) of NerysV2-6.7B and ErebusV1-6.7B\n\n",
"word_embed_proj_dim": 4096
}
|