Hugging Face's logo

TheBlokeAI
/
llama-68m-GPTQ-sharded

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
4-bit precision
gptq
Model card Files Community
llama-68m-GPTQ-sharded
File size: 6,206 Bytes 
a26e784
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
 
{
  "metadata": {
    "total_size": 108218880
  },
  "weight_map": {
    "lm_head.weight": "model-00003-of-00003.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.0.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.0.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.1.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
    "model.layers.1.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
    "model.norm.weight": "model-00002-of-00003.safetensors"
  }
}