abdou-u commited on
Commit
1495683
·
verified ·
1 Parent(s): 0e6cd69

Update: W4A8 optimum-quanto quantized model with quantization map

Browse files
Files changed (4) hide show
  1. README.md +6 -196
  2. config.json +1 -1
  3. model.safetensors +2 -2
  4. quanto_qmap.json +790 -0
README.md CHANGED
@@ -1,199 +1,9 @@
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]
 
1
  ---
2
+ tags:
3
+ - model_hub_mixin
4
  ---
5
 
6
+ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
7
+ - Code: [More Information Needed]
8
+ - Paper: [More Information Needed]
9
+ - Docs: [More Information Needed]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "rope_scaling": null,
23
  "rope_theta": 1000000,
24
  "sliding_window": null,
25
- "tie_word_embeddings": true,
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.52.4",
28
  "use_cache": true,
 
22
  "rope_scaling": null,
23
  "rope_theta": 1000000,
24
  "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.52.4",
28
  "use_cache": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aff089fb6d4408a837f6e72dad9744434779e2c50d80fc9cf94d86455ac0901
3
- size 2384280256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f07357cda3e3dc54ed3a18d8afbaa8fbb92e8cd52bea3cc2fc5c5a8cae9be4
3
+ size 957961200
quanto_qmap.json ADDED
@@ -0,0 +1,790 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model.layers.0.self_attn.q_proj": {
3
+ "weights": "qint4",
4
+ "activations": "qint8"
5
+ },
6
+ "model.layers.0.self_attn.k_proj": {
7
+ "weights": "qint4",
8
+ "activations": "qint8"
9
+ },
10
+ "model.layers.0.self_attn.v_proj": {
11
+ "weights": "qint4",
12
+ "activations": "qint8"
13
+ },
14
+ "model.layers.0.self_attn.o_proj": {
15
+ "weights": "qint4",
16
+ "activations": "qint8"
17
+ },
18
+ "model.layers.0.mlp.gate_proj": {
19
+ "weights": "qint4",
20
+ "activations": "qint8"
21
+ },
22
+ "model.layers.0.mlp.up_proj": {
23
+ "weights": "qint4",
24
+ "activations": "qint8"
25
+ },
26
+ "model.layers.0.mlp.down_proj": {
27
+ "weights": "qint4",
28
+ "activations": "qint8"
29
+ },
30
+ "model.layers.1.self_attn.q_proj": {
31
+ "weights": "qint4",
32
+ "activations": "qint8"
33
+ },
34
+ "model.layers.1.self_attn.k_proj": {
35
+ "weights": "qint4",
36
+ "activations": "qint8"
37
+ },
38
+ "model.layers.1.self_attn.v_proj": {
39
+ "weights": "qint4",
40
+ "activations": "qint8"
41
+ },
42
+ "model.layers.1.self_attn.o_proj": {
43
+ "weights": "qint4",
44
+ "activations": "qint8"
45
+ },
46
+ "model.layers.1.mlp.gate_proj": {
47
+ "weights": "qint4",
48
+ "activations": "qint8"
49
+ },
50
+ "model.layers.1.mlp.up_proj": {
51
+ "weights": "qint4",
52
+ "activations": "qint8"
53
+ },
54
+ "model.layers.1.mlp.down_proj": {
55
+ "weights": "qint4",
56
+ "activations": "qint8"
57
+ },
58
+ "model.layers.2.self_attn.q_proj": {
59
+ "weights": "qint4",
60
+ "activations": "qint8"
61
+ },
62
+ "model.layers.2.self_attn.k_proj": {
63
+ "weights": "qint4",
64
+ "activations": "qint8"
65
+ },
66
+ "model.layers.2.self_attn.v_proj": {
67
+ "weights": "qint4",
68
+ "activations": "qint8"
69
+ },
70
+ "model.layers.2.self_attn.o_proj": {
71
+ "weights": "qint4",
72
+ "activations": "qint8"
73
+ },
74
+ "model.layers.2.mlp.gate_proj": {
75
+ "weights": "qint4",
76
+ "activations": "qint8"
77
+ },
78
+ "model.layers.2.mlp.up_proj": {
79
+ "weights": "qint4",
80
+ "activations": "qint8"
81
+ },
82
+ "model.layers.2.mlp.down_proj": {
83
+ "weights": "qint4",
84
+ "activations": "qint8"
85
+ },
86
+ "model.layers.3.self_attn.q_proj": {
87
+ "weights": "qint4",
88
+ "activations": "qint8"
89
+ },
90
+ "model.layers.3.self_attn.k_proj": {
91
+ "weights": "qint4",
92
+ "activations": "qint8"
93
+ },
94
+ "model.layers.3.self_attn.v_proj": {
95
+ "weights": "qint4",
96
+ "activations": "qint8"
97
+ },
98
+ "model.layers.3.self_attn.o_proj": {
99
+ "weights": "qint4",
100
+ "activations": "qint8"
101
+ },
102
+ "model.layers.3.mlp.gate_proj": {
103
+ "weights": "qint4",
104
+ "activations": "qint8"
105
+ },
106
+ "model.layers.3.mlp.up_proj": {
107
+ "weights": "qint4",
108
+ "activations": "qint8"
109
+ },
110
+ "model.layers.3.mlp.down_proj": {
111
+ "weights": "qint4",
112
+ "activations": "qint8"
113
+ },
114
+ "model.layers.4.self_attn.q_proj": {
115
+ "weights": "qint4",
116
+ "activations": "qint8"
117
+ },
118
+ "model.layers.4.self_attn.k_proj": {
119
+ "weights": "qint4",
120
+ "activations": "qint8"
121
+ },
122
+ "model.layers.4.self_attn.v_proj": {
123
+ "weights": "qint4",
124
+ "activations": "qint8"
125
+ },
126
+ "model.layers.4.self_attn.o_proj": {
127
+ "weights": "qint4",
128
+ "activations": "qint8"
129
+ },
130
+ "model.layers.4.mlp.gate_proj": {
131
+ "weights": "qint4",
132
+ "activations": "qint8"
133
+ },
134
+ "model.layers.4.mlp.up_proj": {
135
+ "weights": "qint4",
136
+ "activations": "qint8"
137
+ },
138
+ "model.layers.4.mlp.down_proj": {
139
+ "weights": "qint4",
140
+ "activations": "qint8"
141
+ },
142
+ "model.layers.5.self_attn.q_proj": {
143
+ "weights": "qint4",
144
+ "activations": "qint8"
145
+ },
146
+ "model.layers.5.self_attn.k_proj": {
147
+ "weights": "qint4",
148
+ "activations": "qint8"
149
+ },
150
+ "model.layers.5.self_attn.v_proj": {
151
+ "weights": "qint4",
152
+ "activations": "qint8"
153
+ },
154
+ "model.layers.5.self_attn.o_proj": {
155
+ "weights": "qint4",
156
+ "activations": "qint8"
157
+ },
158
+ "model.layers.5.mlp.gate_proj": {
159
+ "weights": "qint4",
160
+ "activations": "qint8"
161
+ },
162
+ "model.layers.5.mlp.up_proj": {
163
+ "weights": "qint4",
164
+ "activations": "qint8"
165
+ },
166
+ "model.layers.5.mlp.down_proj": {
167
+ "weights": "qint4",
168
+ "activations": "qint8"
169
+ },
170
+ "model.layers.6.self_attn.q_proj": {
171
+ "weights": "qint4",
172
+ "activations": "qint8"
173
+ },
174
+ "model.layers.6.self_attn.k_proj": {
175
+ "weights": "qint4",
176
+ "activations": "qint8"
177
+ },
178
+ "model.layers.6.self_attn.v_proj": {
179
+ "weights": "qint4",
180
+ "activations": "qint8"
181
+ },
182
+ "model.layers.6.self_attn.o_proj": {
183
+ "weights": "qint4",
184
+ "activations": "qint8"
185
+ },
186
+ "model.layers.6.mlp.gate_proj": {
187
+ "weights": "qint4",
188
+ "activations": "qint8"
189
+ },
190
+ "model.layers.6.mlp.up_proj": {
191
+ "weights": "qint4",
192
+ "activations": "qint8"
193
+ },
194
+ "model.layers.6.mlp.down_proj": {
195
+ "weights": "qint4",
196
+ "activations": "qint8"
197
+ },
198
+ "model.layers.7.self_attn.q_proj": {
199
+ "weights": "qint4",
200
+ "activations": "qint8"
201
+ },
202
+ "model.layers.7.self_attn.k_proj": {
203
+ "weights": "qint4",
204
+ "activations": "qint8"
205
+ },
206
+ "model.layers.7.self_attn.v_proj": {
207
+ "weights": "qint4",
208
+ "activations": "qint8"
209
+ },
210
+ "model.layers.7.self_attn.o_proj": {
211
+ "weights": "qint4",
212
+ "activations": "qint8"
213
+ },
214
+ "model.layers.7.mlp.gate_proj": {
215
+ "weights": "qint4",
216
+ "activations": "qint8"
217
+ },
218
+ "model.layers.7.mlp.up_proj": {
219
+ "weights": "qint4",
220
+ "activations": "qint8"
221
+ },
222
+ "model.layers.7.mlp.down_proj": {
223
+ "weights": "qint4",
224
+ "activations": "qint8"
225
+ },
226
+ "model.layers.8.self_attn.q_proj": {
227
+ "weights": "qint4",
228
+ "activations": "qint8"
229
+ },
230
+ "model.layers.8.self_attn.k_proj": {
231
+ "weights": "qint4",
232
+ "activations": "qint8"
233
+ },
234
+ "model.layers.8.self_attn.v_proj": {
235
+ "weights": "qint4",
236
+ "activations": "qint8"
237
+ },
238
+ "model.layers.8.self_attn.o_proj": {
239
+ "weights": "qint4",
240
+ "activations": "qint8"
241
+ },
242
+ "model.layers.8.mlp.gate_proj": {
243
+ "weights": "qint4",
244
+ "activations": "qint8"
245
+ },
246
+ "model.layers.8.mlp.up_proj": {
247
+ "weights": "qint4",
248
+ "activations": "qint8"
249
+ },
250
+ "model.layers.8.mlp.down_proj": {
251
+ "weights": "qint4",
252
+ "activations": "qint8"
253
+ },
254
+ "model.layers.9.self_attn.q_proj": {
255
+ "weights": "qint4",
256
+ "activations": "qint8"
257
+ },
258
+ "model.layers.9.self_attn.k_proj": {
259
+ "weights": "qint4",
260
+ "activations": "qint8"
261
+ },
262
+ "model.layers.9.self_attn.v_proj": {
263
+ "weights": "qint4",
264
+ "activations": "qint8"
265
+ },
266
+ "model.layers.9.self_attn.o_proj": {
267
+ "weights": "qint4",
268
+ "activations": "qint8"
269
+ },
270
+ "model.layers.9.mlp.gate_proj": {
271
+ "weights": "qint4",
272
+ "activations": "qint8"
273
+ },
274
+ "model.layers.9.mlp.up_proj": {
275
+ "weights": "qint4",
276
+ "activations": "qint8"
277
+ },
278
+ "model.layers.9.mlp.down_proj": {
279
+ "weights": "qint4",
280
+ "activations": "qint8"
281
+ },
282
+ "model.layers.10.self_attn.q_proj": {
283
+ "weights": "qint4",
284
+ "activations": "qint8"
285
+ },
286
+ "model.layers.10.self_attn.k_proj": {
287
+ "weights": "qint4",
288
+ "activations": "qint8"
289
+ },
290
+ "model.layers.10.self_attn.v_proj": {
291
+ "weights": "qint4",
292
+ "activations": "qint8"
293
+ },
294
+ "model.layers.10.self_attn.o_proj": {
295
+ "weights": "qint4",
296
+ "activations": "qint8"
297
+ },
298
+ "model.layers.10.mlp.gate_proj": {
299
+ "weights": "qint4",
300
+ "activations": "qint8"
301
+ },
302
+ "model.layers.10.mlp.up_proj": {
303
+ "weights": "qint4",
304
+ "activations": "qint8"
305
+ },
306
+ "model.layers.10.mlp.down_proj": {
307
+ "weights": "qint4",
308
+ "activations": "qint8"
309
+ },
310
+ "model.layers.11.self_attn.q_proj": {
311
+ "weights": "qint4",
312
+ "activations": "qint8"
313
+ },
314
+ "model.layers.11.self_attn.k_proj": {
315
+ "weights": "qint4",
316
+ "activations": "qint8"
317
+ },
318
+ "model.layers.11.self_attn.v_proj": {
319
+ "weights": "qint4",
320
+ "activations": "qint8"
321
+ },
322
+ "model.layers.11.self_attn.o_proj": {
323
+ "weights": "qint4",
324
+ "activations": "qint8"
325
+ },
326
+ "model.layers.11.mlp.gate_proj": {
327
+ "weights": "qint4",
328
+ "activations": "qint8"
329
+ },
330
+ "model.layers.11.mlp.up_proj": {
331
+ "weights": "qint4",
332
+ "activations": "qint8"
333
+ },
334
+ "model.layers.11.mlp.down_proj": {
335
+ "weights": "qint4",
336
+ "activations": "qint8"
337
+ },
338
+ "model.layers.12.self_attn.q_proj": {
339
+ "weights": "qint4",
340
+ "activations": "qint8"
341
+ },
342
+ "model.layers.12.self_attn.k_proj": {
343
+ "weights": "qint4",
344
+ "activations": "qint8"
345
+ },
346
+ "model.layers.12.self_attn.v_proj": {
347
+ "weights": "qint4",
348
+ "activations": "qint8"
349
+ },
350
+ "model.layers.12.self_attn.o_proj": {
351
+ "weights": "qint4",
352
+ "activations": "qint8"
353
+ },
354
+ "model.layers.12.mlp.gate_proj": {
355
+ "weights": "qint4",
356
+ "activations": "qint8"
357
+ },
358
+ "model.layers.12.mlp.up_proj": {
359
+ "weights": "qint4",
360
+ "activations": "qint8"
361
+ },
362
+ "model.layers.12.mlp.down_proj": {
363
+ "weights": "qint4",
364
+ "activations": "qint8"
365
+ },
366
+ "model.layers.13.self_attn.q_proj": {
367
+ "weights": "qint4",
368
+ "activations": "qint8"
369
+ },
370
+ "model.layers.13.self_attn.k_proj": {
371
+ "weights": "qint4",
372
+ "activations": "qint8"
373
+ },
374
+ "model.layers.13.self_attn.v_proj": {
375
+ "weights": "qint4",
376
+ "activations": "qint8"
377
+ },
378
+ "model.layers.13.self_attn.o_proj": {
379
+ "weights": "qint4",
380
+ "activations": "qint8"
381
+ },
382
+ "model.layers.13.mlp.gate_proj": {
383
+ "weights": "qint4",
384
+ "activations": "qint8"
385
+ },
386
+ "model.layers.13.mlp.up_proj": {
387
+ "weights": "qint4",
388
+ "activations": "qint8"
389
+ },
390
+ "model.layers.13.mlp.down_proj": {
391
+ "weights": "qint4",
392
+ "activations": "qint8"
393
+ },
394
+ "model.layers.14.self_attn.q_proj": {
395
+ "weights": "qint4",
396
+ "activations": "qint8"
397
+ },
398
+ "model.layers.14.self_attn.k_proj": {
399
+ "weights": "qint4",
400
+ "activations": "qint8"
401
+ },
402
+ "model.layers.14.self_attn.v_proj": {
403
+ "weights": "qint4",
404
+ "activations": "qint8"
405
+ },
406
+ "model.layers.14.self_attn.o_proj": {
407
+ "weights": "qint4",
408
+ "activations": "qint8"
409
+ },
410
+ "model.layers.14.mlp.gate_proj": {
411
+ "weights": "qint4",
412
+ "activations": "qint8"
413
+ },
414
+ "model.layers.14.mlp.up_proj": {
415
+ "weights": "qint4",
416
+ "activations": "qint8"
417
+ },
418
+ "model.layers.14.mlp.down_proj": {
419
+ "weights": "qint4",
420
+ "activations": "qint8"
421
+ },
422
+ "model.layers.15.self_attn.q_proj": {
423
+ "weights": "qint4",
424
+ "activations": "qint8"
425
+ },
426
+ "model.layers.15.self_attn.k_proj": {
427
+ "weights": "qint4",
428
+ "activations": "qint8"
429
+ },
430
+ "model.layers.15.self_attn.v_proj": {
431
+ "weights": "qint4",
432
+ "activations": "qint8"
433
+ },
434
+ "model.layers.15.self_attn.o_proj": {
435
+ "weights": "qint4",
436
+ "activations": "qint8"
437
+ },
438
+ "model.layers.15.mlp.gate_proj": {
439
+ "weights": "qint4",
440
+ "activations": "qint8"
441
+ },
442
+ "model.layers.15.mlp.up_proj": {
443
+ "weights": "qint4",
444
+ "activations": "qint8"
445
+ },
446
+ "model.layers.15.mlp.down_proj": {
447
+ "weights": "qint4",
448
+ "activations": "qint8"
449
+ },
450
+ "model.layers.16.self_attn.q_proj": {
451
+ "weights": "qint4",
452
+ "activations": "qint8"
453
+ },
454
+ "model.layers.16.self_attn.k_proj": {
455
+ "weights": "qint4",
456
+ "activations": "qint8"
457
+ },
458
+ "model.layers.16.self_attn.v_proj": {
459
+ "weights": "qint4",
460
+ "activations": "qint8"
461
+ },
462
+ "model.layers.16.self_attn.o_proj": {
463
+ "weights": "qint4",
464
+ "activations": "qint8"
465
+ },
466
+ "model.layers.16.mlp.gate_proj": {
467
+ "weights": "qint4",
468
+ "activations": "qint8"
469
+ },
470
+ "model.layers.16.mlp.up_proj": {
471
+ "weights": "qint4",
472
+ "activations": "qint8"
473
+ },
474
+ "model.layers.16.mlp.down_proj": {
475
+ "weights": "qint4",
476
+ "activations": "qint8"
477
+ },
478
+ "model.layers.17.self_attn.q_proj": {
479
+ "weights": "qint4",
480
+ "activations": "qint8"
481
+ },
482
+ "model.layers.17.self_attn.k_proj": {
483
+ "weights": "qint4",
484
+ "activations": "qint8"
485
+ },
486
+ "model.layers.17.self_attn.v_proj": {
487
+ "weights": "qint4",
488
+ "activations": "qint8"
489
+ },
490
+ "model.layers.17.self_attn.o_proj": {
491
+ "weights": "qint4",
492
+ "activations": "qint8"
493
+ },
494
+ "model.layers.17.mlp.gate_proj": {
495
+ "weights": "qint4",
496
+ "activations": "qint8"
497
+ },
498
+ "model.layers.17.mlp.up_proj": {
499
+ "weights": "qint4",
500
+ "activations": "qint8"
501
+ },
502
+ "model.layers.17.mlp.down_proj": {
503
+ "weights": "qint4",
504
+ "activations": "qint8"
505
+ },
506
+ "model.layers.18.self_attn.q_proj": {
507
+ "weights": "qint4",
508
+ "activations": "qint8"
509
+ },
510
+ "model.layers.18.self_attn.k_proj": {
511
+ "weights": "qint4",
512
+ "activations": "qint8"
513
+ },
514
+ "model.layers.18.self_attn.v_proj": {
515
+ "weights": "qint4",
516
+ "activations": "qint8"
517
+ },
518
+ "model.layers.18.self_attn.o_proj": {
519
+ "weights": "qint4",
520
+ "activations": "qint8"
521
+ },
522
+ "model.layers.18.mlp.gate_proj": {
523
+ "weights": "qint4",
524
+ "activations": "qint8"
525
+ },
526
+ "model.layers.18.mlp.up_proj": {
527
+ "weights": "qint4",
528
+ "activations": "qint8"
529
+ },
530
+ "model.layers.18.mlp.down_proj": {
531
+ "weights": "qint4",
532
+ "activations": "qint8"
533
+ },
534
+ "model.layers.19.self_attn.q_proj": {
535
+ "weights": "qint4",
536
+ "activations": "qint8"
537
+ },
538
+ "model.layers.19.self_attn.k_proj": {
539
+ "weights": "qint4",
540
+ "activations": "qint8"
541
+ },
542
+ "model.layers.19.self_attn.v_proj": {
543
+ "weights": "qint4",
544
+ "activations": "qint8"
545
+ },
546
+ "model.layers.19.self_attn.o_proj": {
547
+ "weights": "qint4",
548
+ "activations": "qint8"
549
+ },
550
+ "model.layers.19.mlp.gate_proj": {
551
+ "weights": "qint4",
552
+ "activations": "qint8"
553
+ },
554
+ "model.layers.19.mlp.up_proj": {
555
+ "weights": "qint4",
556
+ "activations": "qint8"
557
+ },
558
+ "model.layers.19.mlp.down_proj": {
559
+ "weights": "qint4",
560
+ "activations": "qint8"
561
+ },
562
+ "model.layers.20.self_attn.q_proj": {
563
+ "weights": "qint4",
564
+ "activations": "qint8"
565
+ },
566
+ "model.layers.20.self_attn.k_proj": {
567
+ "weights": "qint4",
568
+ "activations": "qint8"
569
+ },
570
+ "model.layers.20.self_attn.v_proj": {
571
+ "weights": "qint4",
572
+ "activations": "qint8"
573
+ },
574
+ "model.layers.20.self_attn.o_proj": {
575
+ "weights": "qint4",
576
+ "activations": "qint8"
577
+ },
578
+ "model.layers.20.mlp.gate_proj": {
579
+ "weights": "qint4",
580
+ "activations": "qint8"
581
+ },
582
+ "model.layers.20.mlp.up_proj": {
583
+ "weights": "qint4",
584
+ "activations": "qint8"
585
+ },
586
+ "model.layers.20.mlp.down_proj": {
587
+ "weights": "qint4",
588
+ "activations": "qint8"
589
+ },
590
+ "model.layers.21.self_attn.q_proj": {
591
+ "weights": "qint4",
592
+ "activations": "qint8"
593
+ },
594
+ "model.layers.21.self_attn.k_proj": {
595
+ "weights": "qint4",
596
+ "activations": "qint8"
597
+ },
598
+ "model.layers.21.self_attn.v_proj": {
599
+ "weights": "qint4",
600
+ "activations": "qint8"
601
+ },
602
+ "model.layers.21.self_attn.o_proj": {
603
+ "weights": "qint4",
604
+ "activations": "qint8"
605
+ },
606
+ "model.layers.21.mlp.gate_proj": {
607
+ "weights": "qint4",
608
+ "activations": "qint8"
609
+ },
610
+ "model.layers.21.mlp.up_proj": {
611
+ "weights": "qint4",
612
+ "activations": "qint8"
613
+ },
614
+ "model.layers.21.mlp.down_proj": {
615
+ "weights": "qint4",
616
+ "activations": "qint8"
617
+ },
618
+ "model.layers.22.self_attn.q_proj": {
619
+ "weights": "qint4",
620
+ "activations": "qint8"
621
+ },
622
+ "model.layers.22.self_attn.k_proj": {
623
+ "weights": "qint4",
624
+ "activations": "qint8"
625
+ },
626
+ "model.layers.22.self_attn.v_proj": {
627
+ "weights": "qint4",
628
+ "activations": "qint8"
629
+ },
630
+ "model.layers.22.self_attn.o_proj": {
631
+ "weights": "qint4",
632
+ "activations": "qint8"
633
+ },
634
+ "model.layers.22.mlp.gate_proj": {
635
+ "weights": "qint4",
636
+ "activations": "qint8"
637
+ },
638
+ "model.layers.22.mlp.up_proj": {
639
+ "weights": "qint4",
640
+ "activations": "qint8"
641
+ },
642
+ "model.layers.22.mlp.down_proj": {
643
+ "weights": "qint4",
644
+ "activations": "qint8"
645
+ },
646
+ "model.layers.23.self_attn.q_proj": {
647
+ "weights": "qint4",
648
+ "activations": "qint8"
649
+ },
650
+ "model.layers.23.self_attn.k_proj": {
651
+ "weights": "qint4",
652
+ "activations": "qint8"
653
+ },
654
+ "model.layers.23.self_attn.v_proj": {
655
+ "weights": "qint4",
656
+ "activations": "qint8"
657
+ },
658
+ "model.layers.23.self_attn.o_proj": {
659
+ "weights": "qint4",
660
+ "activations": "qint8"
661
+ },
662
+ "model.layers.23.mlp.gate_proj": {
663
+ "weights": "qint4",
664
+ "activations": "qint8"
665
+ },
666
+ "model.layers.23.mlp.up_proj": {
667
+ "weights": "qint4",
668
+ "activations": "qint8"
669
+ },
670
+ "model.layers.23.mlp.down_proj": {
671
+ "weights": "qint4",
672
+ "activations": "qint8"
673
+ },
674
+ "model.layers.24.self_attn.q_proj": {
675
+ "weights": "qint4",
676
+ "activations": "qint8"
677
+ },
678
+ "model.layers.24.self_attn.k_proj": {
679
+ "weights": "qint4",
680
+ "activations": "qint8"
681
+ },
682
+ "model.layers.24.self_attn.v_proj": {
683
+ "weights": "qint4",
684
+ "activations": "qint8"
685
+ },
686
+ "model.layers.24.self_attn.o_proj": {
687
+ "weights": "qint4",
688
+ "activations": "qint8"
689
+ },
690
+ "model.layers.24.mlp.gate_proj": {
691
+ "weights": "qint4",
692
+ "activations": "qint8"
693
+ },
694
+ "model.layers.24.mlp.up_proj": {
695
+ "weights": "qint4",
696
+ "activations": "qint8"
697
+ },
698
+ "model.layers.24.mlp.down_proj": {
699
+ "weights": "qint4",
700
+ "activations": "qint8"
701
+ },
702
+ "model.layers.25.self_attn.q_proj": {
703
+ "weights": "qint4",
704
+ "activations": "qint8"
705
+ },
706
+ "model.layers.25.self_attn.k_proj": {
707
+ "weights": "qint4",
708
+ "activations": "qint8"
709
+ },
710
+ "model.layers.25.self_attn.v_proj": {
711
+ "weights": "qint4",
712
+ "activations": "qint8"
713
+ },
714
+ "model.layers.25.self_attn.o_proj": {
715
+ "weights": "qint4",
716
+ "activations": "qint8"
717
+ },
718
+ "model.layers.25.mlp.gate_proj": {
719
+ "weights": "qint4",
720
+ "activations": "qint8"
721
+ },
722
+ "model.layers.25.mlp.up_proj": {
723
+ "weights": "qint4",
724
+ "activations": "qint8"
725
+ },
726
+ "model.layers.25.mlp.down_proj": {
727
+ "weights": "qint4",
728
+ "activations": "qint8"
729
+ },
730
+ "model.layers.26.self_attn.q_proj": {
731
+ "weights": "qint4",
732
+ "activations": "qint8"
733
+ },
734
+ "model.layers.26.self_attn.k_proj": {
735
+ "weights": "qint4",
736
+ "activations": "qint8"
737
+ },
738
+ "model.layers.26.self_attn.v_proj": {
739
+ "weights": "qint4",
740
+ "activations": "qint8"
741
+ },
742
+ "model.layers.26.self_attn.o_proj": {
743
+ "weights": "qint4",
744
+ "activations": "qint8"
745
+ },
746
+ "model.layers.26.mlp.gate_proj": {
747
+ "weights": "qint4",
748
+ "activations": "qint8"
749
+ },
750
+ "model.layers.26.mlp.up_proj": {
751
+ "weights": "qint4",
752
+ "activations": "qint8"
753
+ },
754
+ "model.layers.26.mlp.down_proj": {
755
+ "weights": "qint4",
756
+ "activations": "qint8"
757
+ },
758
+ "model.layers.27.self_attn.q_proj": {
759
+ "weights": "qint4",
760
+ "activations": "qint8"
761
+ },
762
+ "model.layers.27.self_attn.k_proj": {
763
+ "weights": "qint4",
764
+ "activations": "qint8"
765
+ },
766
+ "model.layers.27.self_attn.v_proj": {
767
+ "weights": "qint4",
768
+ "activations": "qint8"
769
+ },
770
+ "model.layers.27.self_attn.o_proj": {
771
+ "weights": "qint4",
772
+ "activations": "qint8"
773
+ },
774
+ "model.layers.27.mlp.gate_proj": {
775
+ "weights": "qint4",
776
+ "activations": "qint8"
777
+ },
778
+ "model.layers.27.mlp.up_proj": {
779
+ "weights": "qint4",
780
+ "activations": "qint8"
781
+ },
782
+ "model.layers.27.mlp.down_proj": {
783
+ "weights": "qint4",
784
+ "activations": "qint8"
785
+ },
786
+ "lm_head": {
787
+ "weights": "qint4",
788
+ "activations": "qint8"
789
+ }
790
+ }