File size: 1,500 Bytes
9c055fd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
51
{
    "_name_or_path": "/covalent/.cache/models/tmppwct651c1qj76h2d",
    "activation": "gelu",
    "alibi": false,
    "apply_residual_connection_post_layernorm": false,
    "architectures": [
        "FalconForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bias": false,
    "bos_token_id": 11,
    "eos_token_id": 11,
    "ffn_hidden_size": 256,
    "hidden_dropout": 0.0,
    "hidden_size": 128,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "falcon",
    "multi_query": true,
    "new_decoder_architecture": false,
    "num_attention_heads": 2,
    "num_hidden_layers": 2,
    "num_kv_heads": 2,
    "num_ln_in_parallel_attn": null,
    "parallel_attn": true,
    "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": 10000.0,
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "vocab_size": 65024,
    "api_key": null
}