Hugging Face's logo

TheBloke
/
MegaDolphin-120b-GPTQ

Text Generation
Transformers
Safetensors
English
llama
conversational
text-generation-inference
4-bit precision
gptq
Model card Files Community
1
MegaDolphin-120b-GPTQ
File size: 1,834 Bytes 
50c5f63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
 
{
    "_name_or_path": "/workspace/process/cognitivecomputations_megadolphin-120b/source",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 32000,
    "hidden_act": "silu",
    "hidden_size": 8192,
    "initializer_range": 0.02,
    "intermediate_size": 28672,
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "num_attention_heads": 64,
    "num_hidden_layers": 140,
    "num_key_value_heads": 8,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "quantization_config": {
        "batch_size": 1,
        "bits": 4,
        "block_name_to_quantize": null,
        "cache_block_outputs": true,
        "damp_percent": 0.1,
        "desc_act": true,
        "exllama_config": {
            "version": 1
        },
        "group_size": -1,
        "max_input_length": null,
        "model_seqlen": null,
        "module_name_preceding_first_block": null,
        "modules_in_block_to_quantize": [
            [
                "self_attn.k_proj",
                "self_attn.v_proj",
                "self_attn.q_proj"
            ],
            [
                "self_attn.o_proj"
            ],
            [
                "mlp.up_proj",
                "mlp.gate_proj"
            ],
            [
                "mlp.down_proj"
            ]
        ],
        "pad_token_id": null,
        "quant_method": "gptq",
        "sym": true,
        "tokenizer": null,
        "true_sequential": true,
        "use_cuda_fp16": false,
        "use_exllama": true
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.37.0.dev0",
    "use_cache": true,
    "vocab_size": 32002
}