Hugging Face's logo

amd
/
Llama-3.1-8B-Instruct-FP8-KV-Quark-test

Safetensors
llama
quark
Model card Files Community
1
Llama-3.1-8B-Instruct-FP8-KV-Quark-test
File size: 4,325 Bytes 
9ca3b76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
 
{
  "_name_or_path": "/group/amdneuralopt/huggingface/pretrained_models/meta-llama/Llama-3.1-8B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "algo_config": null,
    "exclude": [
      "lm_head"
    ],
    "export": {
      "kv_cache_group": [
        "*k_proj",
        "*v_proj"
      ],
      "min_kv_scale": 1.0,
      "pack_method": "reorder",
      "weight_format": "real_quantized",
      "weight_merge_groups": null
    },
    "global_quant_config": {
      "bias": null,
      "input_tensors": {
        "ch_axis": null,
        "dtype": "fp8_e4m3",
        "group_size": null,
        "is_dynamic": false,
        "observer_cls": "PerTensorMinMaxObserver",
        "qscheme": "per_tensor",
        "round_method": null,
        "scale_type": null,
        "symmetric": null
      },
      "output_tensors": null,
      "target_device": null,
      "weight": {
        "ch_axis": null,
        "dtype": "fp8_e4m3",
        "group_size": null,
        "is_dynamic": false,
        "observer_cls": "PerTensorMinMaxObserver",
        "qscheme": "per_tensor",
        "round_method": null,
        "scale_type": null,
        "symmetric": null
      }
    },
    "layer_quant_config": {
      "*k_proj": {
        "bias": null,
        "input_tensors": {
          "ch_axis": null,
          "dtype": "fp8_e4m3",
          "group_size": null,
          "is_dynamic": false,
          "observer_cls": "PerTensorMinMaxObserver",
          "qscheme": "per_tensor",
          "round_method": null,
          "scale_type": null,
          "symmetric": null
        },
        "output_tensors": {
          "ch_axis": null,
          "dtype": "fp8_e4m3",
          "group_size": null,
          "is_dynamic": false,
          "observer_cls": "PerTensorMinMaxObserver",
          "qscheme": "per_tensor",
          "round_method": null,
          "scale_type": null,
          "symmetric": null
        },
        "target_device": null,
        "weight": {
          "ch_axis": null,
          "dtype": "fp8_e4m3",
          "group_size": null,
          "is_dynamic": false,
          "observer_cls": "PerTensorMinMaxObserver",
          "qscheme": "per_tensor",
          "round_method": null,
          "scale_type": null,
          "symmetric": null
        }
      },
      "*v_proj": {
        "bias": null,
        "input_tensors": {
          "ch_axis": null,
          "dtype": "fp8_e4m3",
          "group_size": null,
          "is_dynamic": false,
          "observer_cls": "PerTensorMinMaxObserver",
          "qscheme": "per_tensor",
          "round_method": null,
          "scale_type": null,
          "symmetric": null
        },
        "output_tensors": {
          "ch_axis": null,
          "dtype": "fp8_e4m3",
          "group_size": null,
          "is_dynamic": false,
          "observer_cls": "PerTensorMinMaxObserver",
          "qscheme": "per_tensor",
          "round_method": null,
          "scale_type": null,
          "symmetric": null
        },
        "target_device": null,
        "weight": {
          "ch_axis": null,
          "dtype": "fp8_e4m3",
          "group_size": null,
          "is_dynamic": false,
          "observer_cls": "PerTensorMinMaxObserver",
          "qscheme": "per_tensor",
          "round_method": null,
          "scale_type": null,
          "symmetric": null
        }
      }
    },
    "layer_type_quant_config": {},
    "quant_method": "quark",
    "quant_mode": "eager_mode"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 128256
}