Hugging Face's logo

dwetzel
/
watt-tool-70B-GPTQ-INT4

Safetensors
English
llama
function-calling
tool-use
bfcl
compressed-tensors
Model card Files Community
dwetzel commited on
Commit
efe54d5
·
verified ·
1 Parent(s): 311c59f

Upload LlamaForCausalLM

Browse files
Files changed (12) hide show
  1. README.md +199 -0
  2. config.json +642 -0
  3. generation_config.json +11 -0
  4. model-00001-of-00008.safetensors +3 -0
  5. model-00002-of-00008.safetensors +3 -0
  6. model-00003-of-00008.safetensors +3 -0
  7. model-00004-of-00008.safetensors +3 -0
  8. model-00005-of-00008.safetensors +3 -0
  9. model-00006-of-00008.safetensors +3 -0
  10. model-00007-of-00008.safetensors +3 -0
  11. model-00008-of-00008.safetensors +3 -0
  12. model.safetensors.index.json +0 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,642 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "watt-tool-70B-GPTQ-INT4",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 80,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "quantization_config": {
27
+ "config_groups": {
28
+ "group_0": {
29
+ "input_activations": null,
30
+ "output_activations": null,
31
+ "targets": [
32
+ "Linear"
33
+ ],
34
+ "weights": {
35
+ "actorder": null,
36
+ "block_structure": null,
37
+ "dynamic": false,
38
+ "group_size": 128,
39
+ "num_bits": 4,
40
+ "observer": "minmax",
41
+ "observer_kwargs": {},
42
+ "strategy": "group",
43
+ "symmetric": true,
44
+ "type": "int"
45
+ }
46
+ }
47
+ },
48
+ "format": "pack-quantized",
49
+ "global_compression_ratio": 2.0908934678084408,
50
+ "ignore": [
51
+ "lm_head"
52
+ ],
53
+ "kv_cache_scheme": null,
54
+ "quant_method": "compressed-tensors",
55
+ "quantization_status": "compressed",
56
+ "sparsity_config": {
57
+ "format": "dense",
58
+ "global_sparsity": 0.15516290873237054,
59
+ "ignore": [
60
+ "model.layers.0.self_attn.o_proj",
61
+ "model.layers.0.mlp.gate_proj",
62
+ "model.layers.0.mlp.up_proj",
63
+ "model.layers.0.mlp.down_proj",
64
+ "model.layers.1.self_attn.k_proj",
65
+ "model.layers.1.self_attn.v_proj",
66
+ "model.layers.1.self_attn.o_proj",
67
+ "model.layers.1.mlp.gate_proj",
68
+ "model.layers.1.mlp.up_proj",
69
+ "model.layers.1.mlp.down_proj",
70
+ "model.layers.2.self_attn.q_proj",
71
+ "model.layers.2.self_attn.k_proj",
72
+ "model.layers.2.self_attn.v_proj",
73
+ "model.layers.2.self_attn.o_proj",
74
+ "model.layers.2.mlp.gate_proj",
75
+ "model.layers.2.mlp.up_proj",
76
+ "model.layers.2.mlp.down_proj",
77
+ "model.layers.3.self_attn.q_proj",
78
+ "model.layers.3.self_attn.k_proj",
79
+ "model.layers.3.self_attn.v_proj",
80
+ "model.layers.3.self_attn.o_proj",
81
+ "model.layers.3.mlp.gate_proj",
82
+ "model.layers.3.mlp.up_proj",
83
+ "model.layers.3.mlp.down_proj",
84
+ "model.layers.4.self_attn.q_proj",
85
+ "model.layers.4.self_attn.k_proj",
86
+ "model.layers.4.self_attn.v_proj",
87
+ "model.layers.4.self_attn.o_proj",
88
+ "model.layers.4.mlp.gate_proj",
89
+ "model.layers.4.mlp.up_proj",
90
+ "model.layers.4.mlp.down_proj",
91
+ "model.layers.5.self_attn.q_proj",
92
+ "model.layers.5.self_attn.k_proj",
93
+ "model.layers.5.self_attn.v_proj",
94
+ "model.layers.5.self_attn.o_proj",
95
+ "model.layers.5.mlp.gate_proj",
96
+ "model.layers.5.mlp.up_proj",
97
+ "model.layers.5.mlp.down_proj",
98
+ "model.layers.6.self_attn.q_proj",
99
+ "model.layers.6.self_attn.k_proj",
100
+ "model.layers.6.self_attn.v_proj",
101
+ "model.layers.6.self_attn.o_proj",
102
+ "model.layers.6.mlp.gate_proj",
103
+ "model.layers.6.mlp.up_proj",
104
+ "model.layers.6.mlp.down_proj",
105
+ "model.layers.7.self_attn.q_proj",
106
+ "model.layers.7.self_attn.k_proj",
107
+ "model.layers.7.self_attn.v_proj",
108
+ "model.layers.7.self_attn.o_proj",
109
+ "model.layers.7.mlp.gate_proj",
110
+ "model.layers.7.mlp.up_proj",
111
+ "model.layers.7.mlp.down_proj",
112
+ "model.layers.8.self_attn.q_proj",
113
+ "model.layers.8.self_attn.k_proj",
114
+ "model.layers.8.self_attn.v_proj",
115
+ "model.layers.8.self_attn.o_proj",
116
+ "model.layers.8.mlp.gate_proj",
117
+ "model.layers.8.mlp.up_proj",
118
+ "model.layers.8.mlp.down_proj",
119
+ "model.layers.9.self_attn.q_proj",
120
+ "model.layers.9.self_attn.k_proj",
121
+ "model.layers.9.self_attn.v_proj",
122
+ "model.layers.9.self_attn.o_proj",
123
+ "model.layers.9.mlp.gate_proj",
124
+ "model.layers.9.mlp.up_proj",
125
+ "model.layers.9.mlp.down_proj",
126
+ "model.layers.10.self_attn.q_proj",
127
+ "model.layers.10.self_attn.k_proj",
128
+ "model.layers.10.self_attn.v_proj",
129
+ "model.layers.10.self_attn.o_proj",
130
+ "model.layers.10.mlp.gate_proj",
131
+ "model.layers.10.mlp.up_proj",
132
+ "model.layers.10.mlp.down_proj",
133
+ "model.layers.11.self_attn.q_proj",
134
+ "model.layers.11.self_attn.k_proj",
135
+ "model.layers.11.self_attn.v_proj",
136
+ "model.layers.11.self_attn.o_proj",
137
+ "model.layers.11.mlp.gate_proj",
138
+ "model.layers.11.mlp.up_proj",
139
+ "model.layers.11.mlp.down_proj",
140
+ "model.layers.12.self_attn.q_proj",
141
+ "model.layers.12.self_attn.k_proj",
142
+ "model.layers.12.self_attn.v_proj",
143
+ "model.layers.12.self_attn.o_proj",
144
+ "model.layers.12.mlp.gate_proj",
145
+ "model.layers.12.mlp.up_proj",
146
+ "model.layers.12.mlp.down_proj",
147
+ "model.layers.13.self_attn.q_proj",
148
+ "model.layers.13.self_attn.k_proj",
149
+ "model.layers.13.self_attn.v_proj",
150
+ "model.layers.13.self_attn.o_proj",
151
+ "model.layers.13.mlp.gate_proj",
152
+ "model.layers.13.mlp.up_proj",
153
+ "model.layers.13.mlp.down_proj",
154
+ "model.layers.14.self_attn.q_proj",
155
+ "model.layers.14.self_attn.k_proj",
156
+ "model.layers.14.self_attn.v_proj",
157
+ "model.layers.14.self_attn.o_proj",
158
+ "model.layers.14.mlp.gate_proj",
159
+ "model.layers.14.mlp.up_proj",
160
+ "model.layers.14.mlp.down_proj",
161
+ "model.layers.15.self_attn.q_proj",
162
+ "model.layers.15.self_attn.k_proj",
163
+ "model.layers.15.self_attn.v_proj",
164
+ "model.layers.15.self_attn.o_proj",
165
+ "model.layers.15.mlp.gate_proj",
166
+ "model.layers.15.mlp.up_proj",
167
+ "model.layers.15.mlp.down_proj",
168
+ "model.layers.16.self_attn.q_proj",
169
+ "model.layers.16.self_attn.k_proj",
170
+ "model.layers.16.self_attn.v_proj",
171
+ "model.layers.16.self_attn.o_proj",
172
+ "model.layers.16.mlp.gate_proj",
173
+ "model.layers.16.mlp.up_proj",
174
+ "model.layers.16.mlp.down_proj",
175
+ "model.layers.17.self_attn.q_proj",
176
+ "model.layers.17.self_attn.k_proj",
177
+ "model.layers.17.self_attn.v_proj",
178
+ "model.layers.17.self_attn.o_proj",
179
+ "model.layers.17.mlp.gate_proj",
180
+ "model.layers.17.mlp.up_proj",
181
+ "model.layers.17.mlp.down_proj",
182
+ "model.layers.18.self_attn.q_proj",
183
+ "model.layers.18.self_attn.k_proj",
184
+ "model.layers.18.self_attn.v_proj",
185
+ "model.layers.18.self_attn.o_proj",
186
+ "model.layers.18.mlp.gate_proj",
187
+ "model.layers.18.mlp.up_proj",
188
+ "model.layers.18.mlp.down_proj",
189
+ "model.layers.19.self_attn.q_proj",
190
+ "model.layers.19.self_attn.k_proj",
191
+ "model.layers.19.self_attn.v_proj",
192
+ "model.layers.19.self_attn.o_proj",
193
+ "model.layers.19.mlp.gate_proj",
194
+ "model.layers.19.mlp.up_proj",
195
+ "model.layers.19.mlp.down_proj",
196
+ "model.layers.20.self_attn.q_proj",
197
+ "model.layers.20.self_attn.k_proj",
198
+ "model.layers.20.self_attn.v_proj",
199
+ "model.layers.20.self_attn.o_proj",
200
+ "model.layers.20.mlp.gate_proj",
201
+ "model.layers.20.mlp.up_proj",
202
+ "model.layers.20.mlp.down_proj",
203
+ "model.layers.21.self_attn.q_proj",
204
+ "model.layers.21.self_attn.k_proj",
205
+ "model.layers.21.self_attn.v_proj",
206
+ "model.layers.21.self_attn.o_proj",
207
+ "model.layers.21.mlp.gate_proj",
208
+ "model.layers.21.mlp.up_proj",
209
+ "model.layers.21.mlp.down_proj",
210
+ "model.layers.22.self_attn.q_proj",
211
+ "model.layers.22.self_attn.k_proj",
212
+ "model.layers.22.self_attn.v_proj",
213
+ "model.layers.22.self_attn.o_proj",
214
+ "model.layers.22.mlp.gate_proj",
215
+ "model.layers.22.mlp.up_proj",
216
+ "model.layers.22.mlp.down_proj",
217
+ "model.layers.23.self_attn.q_proj",
218
+ "model.layers.23.self_attn.k_proj",
219
+ "model.layers.23.self_attn.v_proj",
220
+ "model.layers.23.self_attn.o_proj",
221
+ "model.layers.23.mlp.gate_proj",
222
+ "model.layers.23.mlp.up_proj",
223
+ "model.layers.23.mlp.down_proj",
224
+ "model.layers.24.self_attn.q_proj",
225
+ "model.layers.24.self_attn.k_proj",
226
+ "model.layers.24.self_attn.v_proj",
227
+ "model.layers.24.self_attn.o_proj",
228
+ "model.layers.24.mlp.gate_proj",
229
+ "model.layers.24.mlp.up_proj",
230
+ "model.layers.24.mlp.down_proj",
231
+ "model.layers.25.self_attn.q_proj",
232
+ "model.layers.25.self_attn.k_proj",
233
+ "model.layers.25.self_attn.v_proj",
234
+ "model.layers.25.self_attn.o_proj",
235
+ "model.layers.25.mlp.gate_proj",
236
+ "model.layers.25.mlp.up_proj",
237
+ "model.layers.25.mlp.down_proj",
238
+ "model.layers.26.self_attn.q_proj",
239
+ "model.layers.26.self_attn.k_proj",
240
+ "model.layers.26.self_attn.v_proj",
241
+ "model.layers.26.self_attn.o_proj",
242
+ "model.layers.26.mlp.gate_proj",
243
+ "model.layers.26.mlp.up_proj",
244
+ "model.layers.26.mlp.down_proj",
245
+ "model.layers.27.self_attn.q_proj",
246
+ "model.layers.27.self_attn.k_proj",
247
+ "model.layers.27.self_attn.v_proj",
248
+ "model.layers.27.self_attn.o_proj",
249
+ "model.layers.27.mlp.gate_proj",
250
+ "model.layers.27.mlp.up_proj",
251
+ "model.layers.27.mlp.down_proj",
252
+ "model.layers.28.self_attn.q_proj",
253
+ "model.layers.28.self_attn.k_proj",
254
+ "model.layers.28.self_attn.v_proj",
255
+ "model.layers.28.self_attn.o_proj",
256
+ "model.layers.28.mlp.gate_proj",
257
+ "model.layers.28.mlp.up_proj",
258
+ "model.layers.28.mlp.down_proj",
259
+ "model.layers.29.self_attn.q_proj",
260
+ "model.layers.29.self_attn.k_proj",
261
+ "model.layers.29.self_attn.v_proj",
262
+ "model.layers.29.self_attn.o_proj",
263
+ "model.layers.29.mlp.gate_proj",
264
+ "model.layers.29.mlp.up_proj",
265
+ "model.layers.29.mlp.down_proj",
266
+ "model.layers.30.self_attn.q_proj",
267
+ "model.layers.30.self_attn.k_proj",
268
+ "model.layers.30.self_attn.v_proj",
269
+ "model.layers.30.self_attn.o_proj",
270
+ "model.layers.30.mlp.gate_proj",
271
+ "model.layers.30.mlp.up_proj",
272
+ "model.layers.30.mlp.down_proj",
273
+ "model.layers.31.self_attn.q_proj",
274
+ "model.layers.31.self_attn.k_proj",
275
+ "model.layers.31.self_attn.v_proj",
276
+ "model.layers.31.self_attn.o_proj",
277
+ "model.layers.31.mlp.gate_proj",
278
+ "model.layers.31.mlp.up_proj",
279
+ "model.layers.31.mlp.down_proj",
280
+ "model.layers.32.self_attn.q_proj",
281
+ "model.layers.32.self_attn.k_proj",
282
+ "model.layers.32.self_attn.v_proj",
283
+ "model.layers.32.self_attn.o_proj",
284
+ "model.layers.32.mlp.gate_proj",
285
+ "model.layers.32.mlp.up_proj",
286
+ "model.layers.32.mlp.down_proj",
287
+ "model.layers.33.self_attn.q_proj",
288
+ "model.layers.33.self_attn.k_proj",
289
+ "model.layers.33.self_attn.v_proj",
290
+ "model.layers.33.self_attn.o_proj",
291
+ "model.layers.33.mlp.gate_proj",
292
+ "model.layers.33.mlp.up_proj",
293
+ "model.layers.33.mlp.down_proj",
294
+ "model.layers.34.self_attn.q_proj",
295
+ "model.layers.34.self_attn.k_proj",
296
+ "model.layers.34.self_attn.v_proj",
297
+ "model.layers.34.self_attn.o_proj",
298
+ "model.layers.34.mlp.gate_proj",
299
+ "model.layers.34.mlp.up_proj",
300
+ "model.layers.34.mlp.down_proj",
301
+ "model.layers.35.self_attn.q_proj",
302
+ "model.layers.35.self_attn.k_proj",
303
+ "model.layers.35.self_attn.v_proj",
304
+ "model.layers.35.self_attn.o_proj",
305
+ "model.layers.35.mlp.gate_proj",
306
+ "model.layers.35.mlp.up_proj",
307
+ "model.layers.35.mlp.down_proj",
308
+ "model.layers.36.self_attn.q_proj",
309
+ "model.layers.36.self_attn.k_proj",
310
+ "model.layers.36.self_attn.v_proj",
311
+ "model.layers.36.self_attn.o_proj",
312
+ "model.layers.36.mlp.gate_proj",
313
+ "model.layers.36.mlp.up_proj",
314
+ "model.layers.36.mlp.down_proj",
315
+ "model.layers.37.self_attn.q_proj",
316
+ "model.layers.37.self_attn.k_proj",
317
+ "model.layers.37.self_attn.v_proj",
318
+ "model.layers.37.self_attn.o_proj",
319
+ "model.layers.37.mlp.gate_proj",
320
+ "model.layers.37.mlp.up_proj",
321
+ "model.layers.37.mlp.down_proj",
322
+ "model.layers.38.self_attn.q_proj",
323
+ "model.layers.38.self_attn.k_proj",
324
+ "model.layers.38.self_attn.v_proj",
325
+ "model.layers.38.self_attn.o_proj",
326
+ "model.layers.38.mlp.gate_proj",
327
+ "model.layers.38.mlp.up_proj",
328
+ "model.layers.38.mlp.down_proj",
329
+ "model.layers.39.self_attn.q_proj",
330
+ "model.layers.39.self_attn.k_proj",
331
+ "model.layers.39.self_attn.v_proj",
332
+ "model.layers.39.self_attn.o_proj",
333
+ "model.layers.39.mlp.gate_proj",
334
+ "model.layers.39.mlp.up_proj",
335
+ "model.layers.39.mlp.down_proj",
336
+ "model.layers.40.self_attn.q_proj",
337
+ "model.layers.40.self_attn.k_proj",
338
+ "model.layers.40.self_attn.v_proj",
339
+ "model.layers.40.self_attn.o_proj",
340
+ "model.layers.40.mlp.gate_proj",
341
+ "model.layers.40.mlp.up_proj",
342
+ "model.layers.40.mlp.down_proj",
343
+ "model.layers.41.self_attn.q_proj",
344
+ "model.layers.41.self_attn.k_proj",
345
+ "model.layers.41.self_attn.v_proj",
346
+ "model.layers.41.self_attn.o_proj",
347
+ "model.layers.41.mlp.gate_proj",
348
+ "model.layers.41.mlp.up_proj",
349
+ "model.layers.41.mlp.down_proj",
350
+ "model.layers.42.self_attn.q_proj",
351
+ "model.layers.42.self_attn.k_proj",
352
+ "model.layers.42.self_attn.v_proj",
353
+ "model.layers.42.self_attn.o_proj",
354
+ "model.layers.42.mlp.gate_proj",
355
+ "model.layers.42.mlp.up_proj",
356
+ "model.layers.42.mlp.down_proj",
357
+ "model.layers.43.self_attn.q_proj",
358
+ "model.layers.43.self_attn.k_proj",
359
+ "model.layers.43.self_attn.v_proj",
360
+ "model.layers.43.self_attn.o_proj",
361
+ "model.layers.43.mlp.gate_proj",
362
+ "model.layers.43.mlp.up_proj",
363
+ "model.layers.43.mlp.down_proj",
364
+ "model.layers.44.self_attn.q_proj",
365
+ "model.layers.44.self_attn.k_proj",
366
+ "model.layers.44.self_attn.v_proj",
367
+ "model.layers.44.self_attn.o_proj",
368
+ "model.layers.44.mlp.gate_proj",
369
+ "model.layers.44.mlp.up_proj",
370
+ "model.layers.44.mlp.down_proj",
371
+ "model.layers.45.self_attn.q_proj",
372
+ "model.layers.45.self_attn.k_proj",
373
+ "model.layers.45.self_attn.v_proj",
374
+ "model.layers.45.self_attn.o_proj",
375
+ "model.layers.45.mlp.gate_proj",
376
+ "model.layers.45.mlp.up_proj",
377
+ "model.layers.45.mlp.down_proj",
378
+ "model.layers.46.self_attn.q_proj",
379
+ "model.layers.46.self_attn.k_proj",
380
+ "model.layers.46.self_attn.v_proj",
381
+ "model.layers.46.self_attn.o_proj",
382
+ "model.layers.46.mlp.gate_proj",
383
+ "model.layers.46.mlp.up_proj",
384
+ "model.layers.46.mlp.down_proj",
385
+ "model.layers.47.self_attn.q_proj",
386
+ "model.layers.47.self_attn.k_proj",
387
+ "model.layers.47.self_attn.v_proj",
388
+ "model.layers.47.self_attn.o_proj",
389
+ "model.layers.47.mlp.gate_proj",
390
+ "model.layers.47.mlp.up_proj",
391
+ "model.layers.47.mlp.down_proj",
392
+ "model.layers.48.self_attn.q_proj",
393
+ "model.layers.48.self_attn.k_proj",
394
+ "model.layers.48.self_attn.v_proj",
395
+ "model.layers.48.self_attn.o_proj",
396
+ "model.layers.48.mlp.gate_proj",
397
+ "model.layers.48.mlp.up_proj",
398
+ "model.layers.48.mlp.down_proj",
399
+ "model.layers.49.self_attn.q_proj",
400
+ "model.layers.49.self_attn.k_proj",
401
+ "model.layers.49.self_attn.v_proj",
402
+ "model.layers.49.self_attn.o_proj",
403
+ "model.layers.49.mlp.gate_proj",
404
+ "model.layers.49.mlp.up_proj",
405
+ "model.layers.49.mlp.down_proj",
406
+ "model.layers.50.self_attn.q_proj",
407
+ "model.layers.50.self_attn.k_proj",
408
+ "model.layers.50.self_attn.v_proj",
409
+ "model.layers.50.self_attn.o_proj",
410
+ "model.layers.50.mlp.gate_proj",
411
+ "model.layers.50.mlp.up_proj",
412
+ "model.layers.50.mlp.down_proj",
413
+ "model.layers.51.self_attn.q_proj",
414
+ "model.layers.51.self_attn.k_proj",
415
+ "model.layers.51.self_attn.v_proj",
416
+ "model.layers.51.self_attn.o_proj",
417
+ "model.layers.51.mlp.gate_proj",
418
+ "model.layers.51.mlp.up_proj",
419
+ "model.layers.51.mlp.down_proj",
420
+ "model.layers.52.self_attn.q_proj",
421
+ "model.layers.52.self_attn.k_proj",
422
+ "model.layers.52.self_attn.v_proj",
423
+ "model.layers.52.self_attn.o_proj",
424
+ "model.layers.52.mlp.gate_proj",
425
+ "model.layers.52.mlp.up_proj",
426
+ "model.layers.52.mlp.down_proj",
427
+ "model.layers.53.self_attn.q_proj",
428
+ "model.layers.53.self_attn.k_proj",
429
+ "model.layers.53.self_attn.v_proj",
430
+ "model.layers.53.self_attn.o_proj",
431
+ "model.layers.53.mlp.gate_proj",
432
+ "model.layers.53.mlp.up_proj",
433
+ "model.layers.53.mlp.down_proj",
434
+ "model.layers.54.self_attn.q_proj",
435
+ "model.layers.54.self_attn.k_proj",
436
+ "model.layers.54.self_attn.v_proj",
437
+ "model.layers.54.self_attn.o_proj",
438
+ "model.layers.54.mlp.gate_proj",
439
+ "model.layers.54.mlp.up_proj",
440
+ "model.layers.54.mlp.down_proj",
441
+ "model.layers.55.self_attn.q_proj",
442
+ "model.layers.55.self_attn.k_proj",
443
+ "model.layers.55.self_attn.v_proj",
444
+ "model.layers.55.self_attn.o_proj",
445
+ "model.layers.55.mlp.gate_proj",
446
+ "model.layers.55.mlp.up_proj",
447
+ "model.layers.55.mlp.down_proj",
448
+ "model.layers.56.self_attn.q_proj",
449
+ "model.layers.56.self_attn.k_proj",
450
+ "model.layers.56.self_attn.v_proj",
451
+ "model.layers.56.self_attn.o_proj",
452
+ "model.layers.56.mlp.gate_proj",
453
+ "model.layers.56.mlp.up_proj",
454
+ "model.layers.56.mlp.down_proj",
455
+ "model.layers.57.self_attn.q_proj",
456
+ "model.layers.57.self_attn.k_proj",
457
+ "model.layers.57.self_attn.v_proj",
458
+ "model.layers.57.self_attn.o_proj",
459
+ "model.layers.57.mlp.gate_proj",
460
+ "model.layers.57.mlp.up_proj",
461
+ "model.layers.57.mlp.down_proj",
462
+ "model.layers.58.self_attn.q_proj",
463
+ "model.layers.58.self_attn.k_proj",
464
+ "model.layers.58.self_attn.v_proj",
465
+ "model.layers.58.self_attn.o_proj",
466
+ "model.layers.58.mlp.gate_proj",
467
+ "model.layers.58.mlp.up_proj",
468
+ "model.layers.58.mlp.down_proj",
469
+ "model.layers.59.self_attn.q_proj",
470
+ "model.layers.59.self_attn.k_proj",
471
+ "model.layers.59.self_attn.v_proj",
472
+ "model.layers.59.self_attn.o_proj",
473
+ "model.layers.59.mlp.gate_proj",
474
+ "model.layers.59.mlp.up_proj",
475
+ "model.layers.59.mlp.down_proj",
476
+ "model.layers.60.self_attn.q_proj",
477
+ "model.layers.60.self_attn.k_proj",
478
+ "model.layers.60.self_attn.v_proj",
479
+ "model.layers.60.self_attn.o_proj",
480
+ "model.layers.60.mlp.gate_proj",
481
+ "model.layers.60.mlp.up_proj",
482
+ "model.layers.60.mlp.down_proj",
483
+ "model.layers.61.self_attn.q_proj",
484
+ "model.layers.61.self_attn.k_proj",
485
+ "model.layers.61.self_attn.v_proj",
486
+ "model.layers.61.self_attn.o_proj",
487
+ "model.layers.61.mlp.gate_proj",
488
+ "model.layers.61.mlp.up_proj",
489
+ "model.layers.61.mlp.down_proj",
490
+ "model.layers.62.self_attn.q_proj",
491
+ "model.layers.62.self_attn.k_proj",
492
+ "model.layers.62.self_attn.v_proj",
493
+ "model.layers.62.self_attn.o_proj",
494
+ "model.layers.62.mlp.gate_proj",
495
+ "model.layers.62.mlp.up_proj",
496
+ "model.layers.62.mlp.down_proj",
497
+ "model.layers.63.self_attn.q_proj",
498
+ "model.layers.63.self_attn.k_proj",
499
+ "model.layers.63.self_attn.v_proj",
500
+ "model.layers.63.self_attn.o_proj",
501
+ "model.layers.63.mlp.gate_proj",
502
+ "model.layers.63.mlp.up_proj",
503
+ "model.layers.63.mlp.down_proj",
504
+ "model.layers.64.self_attn.q_proj",
505
+ "model.layers.64.self_attn.k_proj",
506
+ "model.layers.64.self_attn.v_proj",
507
+ "model.layers.64.self_attn.o_proj",
508
+ "model.layers.64.mlp.gate_proj",
509
+ "model.layers.64.mlp.up_proj",
510
+ "model.layers.64.mlp.down_proj",
511
+ "model.layers.65.self_attn.q_proj",
512
+ "model.layers.65.self_attn.k_proj",
513
+ "model.layers.65.self_attn.v_proj",
514
+ "model.layers.65.self_attn.o_proj",
515
+ "model.layers.65.mlp.gate_proj",
516
+ "model.layers.65.mlp.up_proj",
517
+ "model.layers.65.mlp.down_proj",
518
+ "model.layers.66.self_attn.q_proj",
519
+ "model.layers.66.self_attn.k_proj",
520
+ "model.layers.66.self_attn.v_proj",
521
+ "model.layers.66.self_attn.o_proj",
522
+ "model.layers.66.mlp.gate_proj",
523
+ "model.layers.66.mlp.up_proj",
524
+ "model.layers.66.mlp.down_proj",
525
+ "model.layers.67.self_attn.q_proj",
526
+ "model.layers.67.self_attn.k_proj",
527
+ "model.layers.67.self_attn.v_proj",
528
+ "model.layers.67.self_attn.o_proj",
529
+ "model.layers.67.mlp.gate_proj",
530
+ "model.layers.67.mlp.up_proj",
531
+ "model.layers.67.mlp.down_proj",
532
+ "model.layers.68.self_attn.q_proj",
533
+ "model.layers.68.self_attn.k_proj",
534
+ "model.layers.68.self_attn.v_proj",
535
+ "model.layers.68.self_attn.o_proj",
536
+ "model.layers.68.mlp.gate_proj",
537
+ "model.layers.68.mlp.up_proj",
538
+ "model.layers.68.mlp.down_proj",
539
+ "model.layers.69.self_attn.q_proj",
540
+ "model.layers.69.self_attn.k_proj",
541
+ "model.layers.69.self_attn.v_proj",
542
+ "model.layers.69.self_attn.o_proj",
543
+ "model.layers.69.mlp.gate_proj",
544
+ "model.layers.69.mlp.up_proj",
545
+ "model.layers.69.mlp.down_proj",
546
+ "model.layers.70.self_attn.q_proj",
547
+ "model.layers.70.self_attn.k_proj",
548
+ "model.layers.70.self_attn.v_proj",
549
+ "model.layers.70.self_attn.o_proj",
550
+ "model.layers.70.mlp.gate_proj",
551
+ "model.layers.70.mlp.up_proj",
552
+ "model.layers.70.mlp.down_proj",
553
+ "model.layers.71.self_attn.q_proj",
554
+ "model.layers.71.self_attn.k_proj",
555
+ "model.layers.71.self_attn.v_proj",
556
+ "model.layers.71.self_attn.o_proj",
557
+ "model.layers.71.mlp.gate_proj",
558
+ "model.layers.71.mlp.up_proj",
559
+ "model.layers.71.mlp.down_proj",
560
+ "model.layers.72.self_attn.q_proj",
561
+ "model.layers.72.self_attn.k_proj",
562
+ "model.layers.72.self_attn.v_proj",
563
+ "model.layers.72.self_attn.o_proj",
564
+ "model.layers.72.mlp.gate_proj",
565
+ "model.layers.72.mlp.up_proj",
566
+ "model.layers.72.mlp.down_proj",
567
+ "model.layers.73.self_attn.q_proj",
568
+ "model.layers.73.self_attn.k_proj",
569
+ "model.layers.73.self_attn.v_proj",
570
+ "model.layers.73.self_attn.o_proj",
571
+ "model.layers.73.mlp.gate_proj",
572
+ "model.layers.73.mlp.up_proj",
573
+ "model.layers.73.mlp.down_proj",
574
+ "model.layers.74.self_attn.q_proj",
575
+ "model.layers.74.self_attn.k_proj",
576
+ "model.layers.74.self_attn.v_proj",
577
+ "model.layers.74.self_attn.o_proj",
578
+ "model.layers.74.mlp.gate_proj",
579
+ "model.layers.74.mlp.up_proj",
580
+ "model.layers.74.mlp.down_proj",
581
+ "model.layers.75.self_attn.q_proj",
582
+ "model.layers.75.self_attn.k_proj",
583
+ "model.layers.75.self_attn.v_proj",
584
+ "model.layers.75.self_attn.o_proj",
585
+ "model.layers.75.mlp.gate_proj",
586
+ "model.layers.75.mlp.up_proj",
587
+ "model.layers.75.mlp.down_proj",
588
+ "model.layers.76.self_attn.q_proj",
589
+ "model.layers.76.self_attn.k_proj",
590
+ "model.layers.76.self_attn.v_proj",
591
+ "model.layers.76.self_attn.o_proj",
592
+ "model.layers.76.mlp.gate_proj",
593
+ "model.layers.76.mlp.up_proj",
594
+ "model.layers.76.mlp.down_proj",
595
+ "model.layers.77.self_attn.q_proj",
596
+ "model.layers.77.self_attn.k_proj",
597
+ "model.layers.77.self_attn.v_proj",
598
+ "model.layers.77.self_attn.o_proj",
599
+ "model.layers.77.mlp.gate_proj",
600
+ "model.layers.77.mlp.up_proj",
601
+ "model.layers.77.mlp.down_proj",
602
+ "model.layers.78.self_attn.q_proj",
603
+ "model.layers.78.self_attn.k_proj",
604
+ "model.layers.78.self_attn.v_proj",
605
+ "model.layers.78.self_attn.o_proj",
606
+ "model.layers.78.mlp.gate_proj",
607
+ "model.layers.78.mlp.up_proj",
608
+ "model.layers.78.mlp.down_proj",
609
+ "model.layers.79.self_attn.q_proj",
610
+ "model.layers.79.self_attn.k_proj",
611
+ "model.layers.79.self_attn.v_proj",
612
+ "model.layers.79.self_attn.o_proj",
613
+ "model.layers.79.mlp.gate_proj",
614
+ "model.layers.79.mlp.up_proj",
615
+ "model.layers.79.mlp.down_proj",
616
+ "lm_head"
617
+ ],
618
+ "registry_requires_subclass": false,
619
+ "sparsity_structure": "unstructured",
620
+ "targets": [
621
+ "model.layers.0.self_attn.q_proj",
622
+ "model.layers.0.self_attn.k_proj",
623
+ "model.layers.0.self_attn.v_proj",
624
+ "model.layers.1.self_attn.q_proj"
625
+ ]
626
+ }
627
+ },
628
+ "rms_norm_eps": 1e-05,
629
+ "rope_scaling": {
630
+ "factor": 8.0,
631
+ "high_freq_factor": 4.0,
632
+ "low_freq_factor": 1.0,
633
+ "original_max_position_embeddings": 8192,
634
+ "rope_type": "llama3"
635
+ },
636
+ "rope_theta": 500000.0,
637
+ "tie_word_embeddings": false,
638
+ "torch_dtype": "bfloat16",
639
+ "transformers_version": "4.48.1",
640
+ "use_cache": false,
641
+ "vocab_size": 128256
642
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "transformers_version": "4.48.1",
10
+ "use_cache": false
11
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57896dff9dcaab68ca2a609f75f173e82e35e6dc76bec0b9209f8ffd2f9f1ac6
3
+ size 4951328944
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cf661bf0635e4e44c8e25c647e075cf0940404012ef9e91ed000b213633856c
3
+ size 4974573776
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b99b308f4e9f259257ca6354aa3d7fc1e25e051aca769edae93bb5dddf4bd1f
3
+ size 4971985416
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099a6c8c60c3172da6aaf9eb3bcf004c1d3ade8c84839f8b1d59e15463d0e824
3
+ size 4933942648
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89936c84ef2f795b4349267580fd6afb8f8f31e9843308e169c1f0fbd6e5d4b5
3
+ size 4974573864
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec66d41775d39cdeb5eb6a3f57199518e67c66ba9456ff1a98af061daec2db5
3
+ size 4974573864
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bbc328f8c09c901bc9b4e5a8eadb27fa70a6afeb38d30533efa4671810cf80c
3
+ size 4971985416
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e3ddd21838fae7beda3a773ac08d99a6cbe3731706b2d75888e28dcbd5816f
3
+ size 4747657600
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff