File size: 1,472 Bytes
8864563
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "/covalent/.cache/models/tmp4b3m5n4khvyviquy",
    "architectures": [
        "GPTNeoXForCausalLM"
    ],
    "attention_bias": true,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "classifier_dropout": 0.1,
    "eos_token_id": 0,
    "hidden_act": "gelu",
    "hidden_dropout": 0.0,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "gpt_neox",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "partial_rotary_factor": 0.25,
    "quantization_config": {
        "_load_in_4bit": false,
        "_load_in_8bit": true,
        "bnb_4bit_compute_dtype": "bfloat16",
        "bnb_4bit_quant_storage": "uint8",
        "bnb_4bit_quant_type": "fp4",
        "bnb_4bit_use_double_quant": false,
        "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"
    },
    "rope_scaling": null,
    "rope_theta": 10000,
    "rotary_emb_base": 10000,
    "rotary_pct": 0.25,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "use_parallel_residual": true,
    "vocab_size": 50304,
    "api_key": null
}