Hugging Face's logo

FabioTrindade
/
Llama-3.1-70B-Instruct-W8A8KV16-WS-TENSOR-AS-TENSOR-Wsym-Asym-SpQ-R1R2R4-SmQ-0.5

Safetensors
llama
8-bit precision
compressed-tensors
Model card Files
xet
 Community
Llama-3.1-70B-Instruct-W8A8KV16-WS-TENSOR-AS-TENSOR-Wsym-Asym-SpQ-R1R2R4-SmQ-0.5
File size: 4,372 Bytes
5b12a88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
164
165
166
167
168
169
170
171
172
173
174
175
{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pad_token_id": null,
  "pretraining_tp": 1,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "int-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "tensor",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": "static",
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "tensor",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        }
      }
    },
    "format": "int-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {
      "config_groups": {
        "R1": {
          "apply": [
            {
              "ignore": [],
              "inverse": false,
              "location": "weight_output",
              "targets": [
                "re:.*embed_tokens$",
                "re:.*o_proj$",
                "re:.*down_proj$"
              ]
            },
            {
              "ignore": [],
              "inverse": true,
              "location": "weight_input",
              "targets": [
                "re:.*q_proj$",
                "re:.*k_proj$",
                "re:.*v_proj$",
                "re:.*up_proj$",
                "re:.*gate_proj$",
                "lm_head"
              ]
            }
          ],
          "head_dim": 128,
          "precision": "torch.float64",
          "randomize": false,
          "requires_grad": false,
          "type": "hadamard"
        },
        "R2": {
          "apply": [
            {
              "ignore": [],
              "inverse": false,
              "location": "weight_output",
              "targets": [
                "re:.*v_proj$"
              ]
            },
            {
              "ignore": [],
              "inverse": true,
              "location": "weight_input",
              "targets": [
                "re:.*o_proj$"
              ]
            }
          ],
          "head_dim": 128,
          "precision": "torch.float64",
          "randomize": false,
          "requires_grad": false,
          "type": "hadamard"
        },
        "R4": {
          "apply": [
            {
              "ignore": [],
              "inverse": false,
              "location": "input",
              "targets": [
                "re:.*down_proj$"
              ]
            },
            {
              "ignore": [],
              "inverse": true,
              "location": "weight_input",
              "targets": [
                "re:.*down_proj$"
              ]
            }
          ],
          "head_dim": 128,
          "precision": "torch.float64",
          "randomize": false,
          "requires_grad": false,
          "type": "hadamard"
        }
      }
    },
    "version": "0.17.1"
  },
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_theta": 500000.0,
    "rope_type": "llama3"
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.10.1",
  "use_cache": true,
  "vocab_size": 128256
}