edwixx commited on
Commit
14dcf98
·
verified ·
1 Parent(s): fc6cca3

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +5 -0
  2. config.json +71 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. quanto_qmap.json +1014 -0
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - model_hub_mixin
4
+ license: mit
5
+ ---
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12288,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "pad_token_id": null,
60
+ "rms_norm_eps": 1e-06,
61
+ "rope_parameters": {
62
+ "rope_theta": 1000000,
63
+ "rope_type": "default"
64
+ },
65
+ "sliding_window": null,
66
+ "tie_word_embeddings": false,
67
+ "transformers_version": "5.3.0",
68
+ "use_cache": true,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "5.3.0",
6
+ "use_cache": true
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:675dd2fec7da429deb10c128b91a5614a08bb324af7ef0029f8ee304a4403f41
3
+ size 8816615740
quanto_qmap.json ADDED
@@ -0,0 +1,1014 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model.layers.0.self_attn.q_proj": {
3
+ "weights": "qfloat8_e4m3fn",
4
+ "activations": "none"
5
+ },
6
+ "model.layers.0.self_attn.k_proj": {
7
+ "weights": "qfloat8_e4m3fn",
8
+ "activations": "none"
9
+ },
10
+ "model.layers.0.self_attn.v_proj": {
11
+ "weights": "qfloat8_e4m3fn",
12
+ "activations": "none"
13
+ },
14
+ "model.layers.0.self_attn.o_proj": {
15
+ "weights": "qfloat8_e4m3fn",
16
+ "activations": "none"
17
+ },
18
+ "model.layers.0.mlp.gate_proj": {
19
+ "weights": "qfloat8_e4m3fn",
20
+ "activations": "none"
21
+ },
22
+ "model.layers.0.mlp.up_proj": {
23
+ "weights": "qfloat8_e4m3fn",
24
+ "activations": "none"
25
+ },
26
+ "model.layers.0.mlp.down_proj": {
27
+ "weights": "qfloat8_e4m3fn",
28
+ "activations": "none"
29
+ },
30
+ "model.layers.1.self_attn.q_proj": {
31
+ "weights": "qfloat8_e4m3fn",
32
+ "activations": "none"
33
+ },
34
+ "model.layers.1.self_attn.k_proj": {
35
+ "weights": "qfloat8_e4m3fn",
36
+ "activations": "none"
37
+ },
38
+ "model.layers.1.self_attn.v_proj": {
39
+ "weights": "qfloat8_e4m3fn",
40
+ "activations": "none"
41
+ },
42
+ "model.layers.1.self_attn.o_proj": {
43
+ "weights": "qfloat8_e4m3fn",
44
+ "activations": "none"
45
+ },
46
+ "model.layers.1.mlp.gate_proj": {
47
+ "weights": "qfloat8_e4m3fn",
48
+ "activations": "none"
49
+ },
50
+ "model.layers.1.mlp.up_proj": {
51
+ "weights": "qfloat8_e4m3fn",
52
+ "activations": "none"
53
+ },
54
+ "model.layers.1.mlp.down_proj": {
55
+ "weights": "qfloat8_e4m3fn",
56
+ "activations": "none"
57
+ },
58
+ "model.layers.2.self_attn.q_proj": {
59
+ "weights": "qfloat8_e4m3fn",
60
+ "activations": "none"
61
+ },
62
+ "model.layers.2.self_attn.k_proj": {
63
+ "weights": "qfloat8_e4m3fn",
64
+ "activations": "none"
65
+ },
66
+ "model.layers.2.self_attn.v_proj": {
67
+ "weights": "qfloat8_e4m3fn",
68
+ "activations": "none"
69
+ },
70
+ "model.layers.2.self_attn.o_proj": {
71
+ "weights": "qfloat8_e4m3fn",
72
+ "activations": "none"
73
+ },
74
+ "model.layers.2.mlp.gate_proj": {
75
+ "weights": "qfloat8_e4m3fn",
76
+ "activations": "none"
77
+ },
78
+ "model.layers.2.mlp.up_proj": {
79
+ "weights": "qfloat8_e4m3fn",
80
+ "activations": "none"
81
+ },
82
+ "model.layers.2.mlp.down_proj": {
83
+ "weights": "qfloat8_e4m3fn",
84
+ "activations": "none"
85
+ },
86
+ "model.layers.3.self_attn.q_proj": {
87
+ "weights": "qfloat8_e4m3fn",
88
+ "activations": "none"
89
+ },
90
+ "model.layers.3.self_attn.k_proj": {
91
+ "weights": "qfloat8_e4m3fn",
92
+ "activations": "none"
93
+ },
94
+ "model.layers.3.self_attn.v_proj": {
95
+ "weights": "qfloat8_e4m3fn",
96
+ "activations": "none"
97
+ },
98
+ "model.layers.3.self_attn.o_proj": {
99
+ "weights": "qfloat8_e4m3fn",
100
+ "activations": "none"
101
+ },
102
+ "model.layers.3.mlp.gate_proj": {
103
+ "weights": "qfloat8_e4m3fn",
104
+ "activations": "none"
105
+ },
106
+ "model.layers.3.mlp.up_proj": {
107
+ "weights": "qfloat8_e4m3fn",
108
+ "activations": "none"
109
+ },
110
+ "model.layers.3.mlp.down_proj": {
111
+ "weights": "qfloat8_e4m3fn",
112
+ "activations": "none"
113
+ },
114
+ "model.layers.4.self_attn.q_proj": {
115
+ "weights": "qfloat8_e4m3fn",
116
+ "activations": "none"
117
+ },
118
+ "model.layers.4.self_attn.k_proj": {
119
+ "weights": "qfloat8_e4m3fn",
120
+ "activations": "none"
121
+ },
122
+ "model.layers.4.self_attn.v_proj": {
123
+ "weights": "qfloat8_e4m3fn",
124
+ "activations": "none"
125
+ },
126
+ "model.layers.4.self_attn.o_proj": {
127
+ "weights": "qfloat8_e4m3fn",
128
+ "activations": "none"
129
+ },
130
+ "model.layers.4.mlp.gate_proj": {
131
+ "weights": "qfloat8_e4m3fn",
132
+ "activations": "none"
133
+ },
134
+ "model.layers.4.mlp.up_proj": {
135
+ "weights": "qfloat8_e4m3fn",
136
+ "activations": "none"
137
+ },
138
+ "model.layers.4.mlp.down_proj": {
139
+ "weights": "qfloat8_e4m3fn",
140
+ "activations": "none"
141
+ },
142
+ "model.layers.5.self_attn.q_proj": {
143
+ "weights": "qfloat8_e4m3fn",
144
+ "activations": "none"
145
+ },
146
+ "model.layers.5.self_attn.k_proj": {
147
+ "weights": "qfloat8_e4m3fn",
148
+ "activations": "none"
149
+ },
150
+ "model.layers.5.self_attn.v_proj": {
151
+ "weights": "qfloat8_e4m3fn",
152
+ "activations": "none"
153
+ },
154
+ "model.layers.5.self_attn.o_proj": {
155
+ "weights": "qfloat8_e4m3fn",
156
+ "activations": "none"
157
+ },
158
+ "model.layers.5.mlp.gate_proj": {
159
+ "weights": "qfloat8_e4m3fn",
160
+ "activations": "none"
161
+ },
162
+ "model.layers.5.mlp.up_proj": {
163
+ "weights": "qfloat8_e4m3fn",
164
+ "activations": "none"
165
+ },
166
+ "model.layers.5.mlp.down_proj": {
167
+ "weights": "qfloat8_e4m3fn",
168
+ "activations": "none"
169
+ },
170
+ "model.layers.6.self_attn.q_proj": {
171
+ "weights": "qfloat8_e4m3fn",
172
+ "activations": "none"
173
+ },
174
+ "model.layers.6.self_attn.k_proj": {
175
+ "weights": "qfloat8_e4m3fn",
176
+ "activations": "none"
177
+ },
178
+ "model.layers.6.self_attn.v_proj": {
179
+ "weights": "qfloat8_e4m3fn",
180
+ "activations": "none"
181
+ },
182
+ "model.layers.6.self_attn.o_proj": {
183
+ "weights": "qfloat8_e4m3fn",
184
+ "activations": "none"
185
+ },
186
+ "model.layers.6.mlp.gate_proj": {
187
+ "weights": "qfloat8_e4m3fn",
188
+ "activations": "none"
189
+ },
190
+ "model.layers.6.mlp.up_proj": {
191
+ "weights": "qfloat8_e4m3fn",
192
+ "activations": "none"
193
+ },
194
+ "model.layers.6.mlp.down_proj": {
195
+ "weights": "qfloat8_e4m3fn",
196
+ "activations": "none"
197
+ },
198
+ "model.layers.7.self_attn.q_proj": {
199
+ "weights": "qfloat8_e4m3fn",
200
+ "activations": "none"
201
+ },
202
+ "model.layers.7.self_attn.k_proj": {
203
+ "weights": "qfloat8_e4m3fn",
204
+ "activations": "none"
205
+ },
206
+ "model.layers.7.self_attn.v_proj": {
207
+ "weights": "qfloat8_e4m3fn",
208
+ "activations": "none"
209
+ },
210
+ "model.layers.7.self_attn.o_proj": {
211
+ "weights": "qfloat8_e4m3fn",
212
+ "activations": "none"
213
+ },
214
+ "model.layers.7.mlp.gate_proj": {
215
+ "weights": "qfloat8_e4m3fn",
216
+ "activations": "none"
217
+ },
218
+ "model.layers.7.mlp.up_proj": {
219
+ "weights": "qfloat8_e4m3fn",
220
+ "activations": "none"
221
+ },
222
+ "model.layers.7.mlp.down_proj": {
223
+ "weights": "qfloat8_e4m3fn",
224
+ "activations": "none"
225
+ },
226
+ "model.layers.8.self_attn.q_proj": {
227
+ "weights": "qfloat8_e4m3fn",
228
+ "activations": "none"
229
+ },
230
+ "model.layers.8.self_attn.k_proj": {
231
+ "weights": "qfloat8_e4m3fn",
232
+ "activations": "none"
233
+ },
234
+ "model.layers.8.self_attn.v_proj": {
235
+ "weights": "qfloat8_e4m3fn",
236
+ "activations": "none"
237
+ },
238
+ "model.layers.8.self_attn.o_proj": {
239
+ "weights": "qfloat8_e4m3fn",
240
+ "activations": "none"
241
+ },
242
+ "model.layers.8.mlp.gate_proj": {
243
+ "weights": "qfloat8_e4m3fn",
244
+ "activations": "none"
245
+ },
246
+ "model.layers.8.mlp.up_proj": {
247
+ "weights": "qfloat8_e4m3fn",
248
+ "activations": "none"
249
+ },
250
+ "model.layers.8.mlp.down_proj": {
251
+ "weights": "qfloat8_e4m3fn",
252
+ "activations": "none"
253
+ },
254
+ "model.layers.9.self_attn.q_proj": {
255
+ "weights": "qfloat8_e4m3fn",
256
+ "activations": "none"
257
+ },
258
+ "model.layers.9.self_attn.k_proj": {
259
+ "weights": "qfloat8_e4m3fn",
260
+ "activations": "none"
261
+ },
262
+ "model.layers.9.self_attn.v_proj": {
263
+ "weights": "qfloat8_e4m3fn",
264
+ "activations": "none"
265
+ },
266
+ "model.layers.9.self_attn.o_proj": {
267
+ "weights": "qfloat8_e4m3fn",
268
+ "activations": "none"
269
+ },
270
+ "model.layers.9.mlp.gate_proj": {
271
+ "weights": "qfloat8_e4m3fn",
272
+ "activations": "none"
273
+ },
274
+ "model.layers.9.mlp.up_proj": {
275
+ "weights": "qfloat8_e4m3fn",
276
+ "activations": "none"
277
+ },
278
+ "model.layers.9.mlp.down_proj": {
279
+ "weights": "qfloat8_e4m3fn",
280
+ "activations": "none"
281
+ },
282
+ "model.layers.10.self_attn.q_proj": {
283
+ "weights": "qfloat8_e4m3fn",
284
+ "activations": "none"
285
+ },
286
+ "model.layers.10.self_attn.k_proj": {
287
+ "weights": "qfloat8_e4m3fn",
288
+ "activations": "none"
289
+ },
290
+ "model.layers.10.self_attn.v_proj": {
291
+ "weights": "qfloat8_e4m3fn",
292
+ "activations": "none"
293
+ },
294
+ "model.layers.10.self_attn.o_proj": {
295
+ "weights": "qfloat8_e4m3fn",
296
+ "activations": "none"
297
+ },
298
+ "model.layers.10.mlp.gate_proj": {
299
+ "weights": "qfloat8_e4m3fn",
300
+ "activations": "none"
301
+ },
302
+ "model.layers.10.mlp.up_proj": {
303
+ "weights": "qfloat8_e4m3fn",
304
+ "activations": "none"
305
+ },
306
+ "model.layers.10.mlp.down_proj": {
307
+ "weights": "qfloat8_e4m3fn",
308
+ "activations": "none"
309
+ },
310
+ "model.layers.11.self_attn.q_proj": {
311
+ "weights": "qfloat8_e4m3fn",
312
+ "activations": "none"
313
+ },
314
+ "model.layers.11.self_attn.k_proj": {
315
+ "weights": "qfloat8_e4m3fn",
316
+ "activations": "none"
317
+ },
318
+ "model.layers.11.self_attn.v_proj": {
319
+ "weights": "qfloat8_e4m3fn",
320
+ "activations": "none"
321
+ },
322
+ "model.layers.11.self_attn.o_proj": {
323
+ "weights": "qfloat8_e4m3fn",
324
+ "activations": "none"
325
+ },
326
+ "model.layers.11.mlp.gate_proj": {
327
+ "weights": "qfloat8_e4m3fn",
328
+ "activations": "none"
329
+ },
330
+ "model.layers.11.mlp.up_proj": {
331
+ "weights": "qfloat8_e4m3fn",
332
+ "activations": "none"
333
+ },
334
+ "model.layers.11.mlp.down_proj": {
335
+ "weights": "qfloat8_e4m3fn",
336
+ "activations": "none"
337
+ },
338
+ "model.layers.12.self_attn.q_proj": {
339
+ "weights": "qfloat8_e4m3fn",
340
+ "activations": "none"
341
+ },
342
+ "model.layers.12.self_attn.k_proj": {
343
+ "weights": "qfloat8_e4m3fn",
344
+ "activations": "none"
345
+ },
346
+ "model.layers.12.self_attn.v_proj": {
347
+ "weights": "qfloat8_e4m3fn",
348
+ "activations": "none"
349
+ },
350
+ "model.layers.12.self_attn.o_proj": {
351
+ "weights": "qfloat8_e4m3fn",
352
+ "activations": "none"
353
+ },
354
+ "model.layers.12.mlp.gate_proj": {
355
+ "weights": "qfloat8_e4m3fn",
356
+ "activations": "none"
357
+ },
358
+ "model.layers.12.mlp.up_proj": {
359
+ "weights": "qfloat8_e4m3fn",
360
+ "activations": "none"
361
+ },
362
+ "model.layers.12.mlp.down_proj": {
363
+ "weights": "qfloat8_e4m3fn",
364
+ "activations": "none"
365
+ },
366
+ "model.layers.13.self_attn.q_proj": {
367
+ "weights": "qfloat8_e4m3fn",
368
+ "activations": "none"
369
+ },
370
+ "model.layers.13.self_attn.k_proj": {
371
+ "weights": "qfloat8_e4m3fn",
372
+ "activations": "none"
373
+ },
374
+ "model.layers.13.self_attn.v_proj": {
375
+ "weights": "qfloat8_e4m3fn",
376
+ "activations": "none"
377
+ },
378
+ "model.layers.13.self_attn.o_proj": {
379
+ "weights": "qfloat8_e4m3fn",
380
+ "activations": "none"
381
+ },
382
+ "model.layers.13.mlp.gate_proj": {
383
+ "weights": "qfloat8_e4m3fn",
384
+ "activations": "none"
385
+ },
386
+ "model.layers.13.mlp.up_proj": {
387
+ "weights": "qfloat8_e4m3fn",
388
+ "activations": "none"
389
+ },
390
+ "model.layers.13.mlp.down_proj": {
391
+ "weights": "qfloat8_e4m3fn",
392
+ "activations": "none"
393
+ },
394
+ "model.layers.14.self_attn.q_proj": {
395
+ "weights": "qfloat8_e4m3fn",
396
+ "activations": "none"
397
+ },
398
+ "model.layers.14.self_attn.k_proj": {
399
+ "weights": "qfloat8_e4m3fn",
400
+ "activations": "none"
401
+ },
402
+ "model.layers.14.self_attn.v_proj": {
403
+ "weights": "qfloat8_e4m3fn",
404
+ "activations": "none"
405
+ },
406
+ "model.layers.14.self_attn.o_proj": {
407
+ "weights": "qfloat8_e4m3fn",
408
+ "activations": "none"
409
+ },
410
+ "model.layers.14.mlp.gate_proj": {
411
+ "weights": "qfloat8_e4m3fn",
412
+ "activations": "none"
413
+ },
414
+ "model.layers.14.mlp.up_proj": {
415
+ "weights": "qfloat8_e4m3fn",
416
+ "activations": "none"
417
+ },
418
+ "model.layers.14.mlp.down_proj": {
419
+ "weights": "qfloat8_e4m3fn",
420
+ "activations": "none"
421
+ },
422
+ "model.layers.15.self_attn.q_proj": {
423
+ "weights": "qfloat8_e4m3fn",
424
+ "activations": "none"
425
+ },
426
+ "model.layers.15.self_attn.k_proj": {
427
+ "weights": "qfloat8_e4m3fn",
428
+ "activations": "none"
429
+ },
430
+ "model.layers.15.self_attn.v_proj": {
431
+ "weights": "qfloat8_e4m3fn",
432
+ "activations": "none"
433
+ },
434
+ "model.layers.15.self_attn.o_proj": {
435
+ "weights": "qfloat8_e4m3fn",
436
+ "activations": "none"
437
+ },
438
+ "model.layers.15.mlp.gate_proj": {
439
+ "weights": "qfloat8_e4m3fn",
440
+ "activations": "none"
441
+ },
442
+ "model.layers.15.mlp.up_proj": {
443
+ "weights": "qfloat8_e4m3fn",
444
+ "activations": "none"
445
+ },
446
+ "model.layers.15.mlp.down_proj": {
447
+ "weights": "qfloat8_e4m3fn",
448
+ "activations": "none"
449
+ },
450
+ "model.layers.16.self_attn.q_proj": {
451
+ "weights": "qfloat8_e4m3fn",
452
+ "activations": "none"
453
+ },
454
+ "model.layers.16.self_attn.k_proj": {
455
+ "weights": "qfloat8_e4m3fn",
456
+ "activations": "none"
457
+ },
458
+ "model.layers.16.self_attn.v_proj": {
459
+ "weights": "qfloat8_e4m3fn",
460
+ "activations": "none"
461
+ },
462
+ "model.layers.16.self_attn.o_proj": {
463
+ "weights": "qfloat8_e4m3fn",
464
+ "activations": "none"
465
+ },
466
+ "model.layers.16.mlp.gate_proj": {
467
+ "weights": "qfloat8_e4m3fn",
468
+ "activations": "none"
469
+ },
470
+ "model.layers.16.mlp.up_proj": {
471
+ "weights": "qfloat8_e4m3fn",
472
+ "activations": "none"
473
+ },
474
+ "model.layers.16.mlp.down_proj": {
475
+ "weights": "qfloat8_e4m3fn",
476
+ "activations": "none"
477
+ },
478
+ "model.layers.17.self_attn.q_proj": {
479
+ "weights": "qfloat8_e4m3fn",
480
+ "activations": "none"
481
+ },
482
+ "model.layers.17.self_attn.k_proj": {
483
+ "weights": "qfloat8_e4m3fn",
484
+ "activations": "none"
485
+ },
486
+ "model.layers.17.self_attn.v_proj": {
487
+ "weights": "qfloat8_e4m3fn",
488
+ "activations": "none"
489
+ },
490
+ "model.layers.17.self_attn.o_proj": {
491
+ "weights": "qfloat8_e4m3fn",
492
+ "activations": "none"
493
+ },
494
+ "model.layers.17.mlp.gate_proj": {
495
+ "weights": "qfloat8_e4m3fn",
496
+ "activations": "none"
497
+ },
498
+ "model.layers.17.mlp.up_proj": {
499
+ "weights": "qfloat8_e4m3fn",
500
+ "activations": "none"
501
+ },
502
+ "model.layers.17.mlp.down_proj": {
503
+ "weights": "qfloat8_e4m3fn",
504
+ "activations": "none"
505
+ },
506
+ "model.layers.18.self_attn.q_proj": {
507
+ "weights": "qfloat8_e4m3fn",
508
+ "activations": "none"
509
+ },
510
+ "model.layers.18.self_attn.k_proj": {
511
+ "weights": "qfloat8_e4m3fn",
512
+ "activations": "none"
513
+ },
514
+ "model.layers.18.self_attn.v_proj": {
515
+ "weights": "qfloat8_e4m3fn",
516
+ "activations": "none"
517
+ },
518
+ "model.layers.18.self_attn.o_proj": {
519
+ "weights": "qfloat8_e4m3fn",
520
+ "activations": "none"
521
+ },
522
+ "model.layers.18.mlp.gate_proj": {
523
+ "weights": "qfloat8_e4m3fn",
524
+ "activations": "none"
525
+ },
526
+ "model.layers.18.mlp.up_proj": {
527
+ "weights": "qfloat8_e4m3fn",
528
+ "activations": "none"
529
+ },
530
+ "model.layers.18.mlp.down_proj": {
531
+ "weights": "qfloat8_e4m3fn",
532
+ "activations": "none"
533
+ },
534
+ "model.layers.19.self_attn.q_proj": {
535
+ "weights": "qfloat8_e4m3fn",
536
+ "activations": "none"
537
+ },
538
+ "model.layers.19.self_attn.k_proj": {
539
+ "weights": "qfloat8_e4m3fn",
540
+ "activations": "none"
541
+ },
542
+ "model.layers.19.self_attn.v_proj": {
543
+ "weights": "qfloat8_e4m3fn",
544
+ "activations": "none"
545
+ },
546
+ "model.layers.19.self_attn.o_proj": {
547
+ "weights": "qfloat8_e4m3fn",
548
+ "activations": "none"
549
+ },
550
+ "model.layers.19.mlp.gate_proj": {
551
+ "weights": "qfloat8_e4m3fn",
552
+ "activations": "none"
553
+ },
554
+ "model.layers.19.mlp.up_proj": {
555
+ "weights": "qfloat8_e4m3fn",
556
+ "activations": "none"
557
+ },
558
+ "model.layers.19.mlp.down_proj": {
559
+ "weights": "qfloat8_e4m3fn",
560
+ "activations": "none"
561
+ },
562
+ "model.layers.20.self_attn.q_proj": {
563
+ "weights": "qfloat8_e4m3fn",
564
+ "activations": "none"
565
+ },
566
+ "model.layers.20.self_attn.k_proj": {
567
+ "weights": "qfloat8_e4m3fn",
568
+ "activations": "none"
569
+ },
570
+ "model.layers.20.self_attn.v_proj": {
571
+ "weights": "qfloat8_e4m3fn",
572
+ "activations": "none"
573
+ },
574
+ "model.layers.20.self_attn.o_proj": {
575
+ "weights": "qfloat8_e4m3fn",
576
+ "activations": "none"
577
+ },
578
+ "model.layers.20.mlp.gate_proj": {
579
+ "weights": "qfloat8_e4m3fn",
580
+ "activations": "none"
581
+ },
582
+ "model.layers.20.mlp.up_proj": {
583
+ "weights": "qfloat8_e4m3fn",
584
+ "activations": "none"
585
+ },
586
+ "model.layers.20.mlp.down_proj": {
587
+ "weights": "qfloat8_e4m3fn",
588
+ "activations": "none"
589
+ },
590
+ "model.layers.21.self_attn.q_proj": {
591
+ "weights": "qfloat8_e4m3fn",
592
+ "activations": "none"
593
+ },
594
+ "model.layers.21.self_attn.k_proj": {
595
+ "weights": "qfloat8_e4m3fn",
596
+ "activations": "none"
597
+ },
598
+ "model.layers.21.self_attn.v_proj": {
599
+ "weights": "qfloat8_e4m3fn",
600
+ "activations": "none"
601
+ },
602
+ "model.layers.21.self_attn.o_proj": {
603
+ "weights": "qfloat8_e4m3fn",
604
+ "activations": "none"
605
+ },
606
+ "model.layers.21.mlp.gate_proj": {
607
+ "weights": "qfloat8_e4m3fn",
608
+ "activations": "none"
609
+ },
610
+ "model.layers.21.mlp.up_proj": {
611
+ "weights": "qfloat8_e4m3fn",
612
+ "activations": "none"
613
+ },
614
+ "model.layers.21.mlp.down_proj": {
615
+ "weights": "qfloat8_e4m3fn",
616
+ "activations": "none"
617
+ },
618
+ "model.layers.22.self_attn.q_proj": {
619
+ "weights": "qfloat8_e4m3fn",
620
+ "activations": "none"
621
+ },
622
+ "model.layers.22.self_attn.k_proj": {
623
+ "weights": "qfloat8_e4m3fn",
624
+ "activations": "none"
625
+ },
626
+ "model.layers.22.self_attn.v_proj": {
627
+ "weights": "qfloat8_e4m3fn",
628
+ "activations": "none"
629
+ },
630
+ "model.layers.22.self_attn.o_proj": {
631
+ "weights": "qfloat8_e4m3fn",
632
+ "activations": "none"
633
+ },
634
+ "model.layers.22.mlp.gate_proj": {
635
+ "weights": "qfloat8_e4m3fn",
636
+ "activations": "none"
637
+ },
638
+ "model.layers.22.mlp.up_proj": {
639
+ "weights": "qfloat8_e4m3fn",
640
+ "activations": "none"
641
+ },
642
+ "model.layers.22.mlp.down_proj": {
643
+ "weights": "qfloat8_e4m3fn",
644
+ "activations": "none"
645
+ },
646
+ "model.layers.23.self_attn.q_proj": {
647
+ "weights": "qfloat8_e4m3fn",
648
+ "activations": "none"
649
+ },
650
+ "model.layers.23.self_attn.k_proj": {
651
+ "weights": "qfloat8_e4m3fn",
652
+ "activations": "none"
653
+ },
654
+ "model.layers.23.self_attn.v_proj": {
655
+ "weights": "qfloat8_e4m3fn",
656
+ "activations": "none"
657
+ },
658
+ "model.layers.23.self_attn.o_proj": {
659
+ "weights": "qfloat8_e4m3fn",
660
+ "activations": "none"
661
+ },
662
+ "model.layers.23.mlp.gate_proj": {
663
+ "weights": "qfloat8_e4m3fn",
664
+ "activations": "none"
665
+ },
666
+ "model.layers.23.mlp.up_proj": {
667
+ "weights": "qfloat8_e4m3fn",
668
+ "activations": "none"
669
+ },
670
+ "model.layers.23.mlp.down_proj": {
671
+ "weights": "qfloat8_e4m3fn",
672
+ "activations": "none"
673
+ },
674
+ "model.layers.24.self_attn.q_proj": {
675
+ "weights": "qfloat8_e4m3fn",
676
+ "activations": "none"
677
+ },
678
+ "model.layers.24.self_attn.k_proj": {
679
+ "weights": "qfloat8_e4m3fn",
680
+ "activations": "none"
681
+ },
682
+ "model.layers.24.self_attn.v_proj": {
683
+ "weights": "qfloat8_e4m3fn",
684
+ "activations": "none"
685
+ },
686
+ "model.layers.24.self_attn.o_proj": {
687
+ "weights": "qfloat8_e4m3fn",
688
+ "activations": "none"
689
+ },
690
+ "model.layers.24.mlp.gate_proj": {
691
+ "weights": "qfloat8_e4m3fn",
692
+ "activations": "none"
693
+ },
694
+ "model.layers.24.mlp.up_proj": {
695
+ "weights": "qfloat8_e4m3fn",
696
+ "activations": "none"
697
+ },
698
+ "model.layers.24.mlp.down_proj": {
699
+ "weights": "qfloat8_e4m3fn",
700
+ "activations": "none"
701
+ },
702
+ "model.layers.25.self_attn.q_proj": {
703
+ "weights": "qfloat8_e4m3fn",
704
+ "activations": "none"
705
+ },
706
+ "model.layers.25.self_attn.k_proj": {
707
+ "weights": "qfloat8_e4m3fn",
708
+ "activations": "none"
709
+ },
710
+ "model.layers.25.self_attn.v_proj": {
711
+ "weights": "qfloat8_e4m3fn",
712
+ "activations": "none"
713
+ },
714
+ "model.layers.25.self_attn.o_proj": {
715
+ "weights": "qfloat8_e4m3fn",
716
+ "activations": "none"
717
+ },
718
+ "model.layers.25.mlp.gate_proj": {
719
+ "weights": "qfloat8_e4m3fn",
720
+ "activations": "none"
721
+ },
722
+ "model.layers.25.mlp.up_proj": {
723
+ "weights": "qfloat8_e4m3fn",
724
+ "activations": "none"
725
+ },
726
+ "model.layers.25.mlp.down_proj": {
727
+ "weights": "qfloat8_e4m3fn",
728
+ "activations": "none"
729
+ },
730
+ "model.layers.26.self_attn.q_proj": {
731
+ "weights": "qfloat8_e4m3fn",
732
+ "activations": "none"
733
+ },
734
+ "model.layers.26.self_attn.k_proj": {
735
+ "weights": "qfloat8_e4m3fn",
736
+ "activations": "none"
737
+ },
738
+ "model.layers.26.self_attn.v_proj": {
739
+ "weights": "qfloat8_e4m3fn",
740
+ "activations": "none"
741
+ },
742
+ "model.layers.26.self_attn.o_proj": {
743
+ "weights": "qfloat8_e4m3fn",
744
+ "activations": "none"
745
+ },
746
+ "model.layers.26.mlp.gate_proj": {
747
+ "weights": "qfloat8_e4m3fn",
748
+ "activations": "none"
749
+ },
750
+ "model.layers.26.mlp.up_proj": {
751
+ "weights": "qfloat8_e4m3fn",
752
+ "activations": "none"
753
+ },
754
+ "model.layers.26.mlp.down_proj": {
755
+ "weights": "qfloat8_e4m3fn",
756
+ "activations": "none"
757
+ },
758
+ "model.layers.27.self_attn.q_proj": {
759
+ "weights": "qfloat8_e4m3fn",
760
+ "activations": "none"
761
+ },
762
+ "model.layers.27.self_attn.k_proj": {
763
+ "weights": "qfloat8_e4m3fn",
764
+ "activations": "none"
765
+ },
766
+ "model.layers.27.self_attn.v_proj": {
767
+ "weights": "qfloat8_e4m3fn",
768
+ "activations": "none"
769
+ },
770
+ "model.layers.27.self_attn.o_proj": {
771
+ "weights": "qfloat8_e4m3fn",
772
+ "activations": "none"
773
+ },
774
+ "model.layers.27.mlp.gate_proj": {
775
+ "weights": "qfloat8_e4m3fn",
776
+ "activations": "none"
777
+ },
778
+ "model.layers.27.mlp.up_proj": {
779
+ "weights": "qfloat8_e4m3fn",
780
+ "activations": "none"
781
+ },
782
+ "model.layers.27.mlp.down_proj": {
783
+ "weights": "qfloat8_e4m3fn",
784
+ "activations": "none"
785
+ },
786
+ "model.layers.28.self_attn.q_proj": {
787
+ "weights": "qfloat8_e4m3fn",
788
+ "activations": "none"
789
+ },
790
+ "model.layers.28.self_attn.k_proj": {
791
+ "weights": "qfloat8_e4m3fn",
792
+ "activations": "none"
793
+ },
794
+ "model.layers.28.self_attn.v_proj": {
795
+ "weights": "qfloat8_e4m3fn",
796
+ "activations": "none"
797
+ },
798
+ "model.layers.28.self_attn.o_proj": {
799
+ "weights": "qfloat8_e4m3fn",
800
+ "activations": "none"
801
+ },
802
+ "model.layers.28.mlp.gate_proj": {
803
+ "weights": "qfloat8_e4m3fn",
804
+ "activations": "none"
805
+ },
806
+ "model.layers.28.mlp.up_proj": {
807
+ "weights": "qfloat8_e4m3fn",
808
+ "activations": "none"
809
+ },
810
+ "model.layers.28.mlp.down_proj": {
811
+ "weights": "qfloat8_e4m3fn",
812
+ "activations": "none"
813
+ },
814
+ "model.layers.29.self_attn.q_proj": {
815
+ "weights": "qfloat8_e4m3fn",
816
+ "activations": "none"
817
+ },
818
+ "model.layers.29.self_attn.k_proj": {
819
+ "weights": "qfloat8_e4m3fn",
820
+ "activations": "none"
821
+ },
822
+ "model.layers.29.self_attn.v_proj": {
823
+ "weights": "qfloat8_e4m3fn",
824
+ "activations": "none"
825
+ },
826
+ "model.layers.29.self_attn.o_proj": {
827
+ "weights": "qfloat8_e4m3fn",
828
+ "activations": "none"
829
+ },
830
+ "model.layers.29.mlp.gate_proj": {
831
+ "weights": "qfloat8_e4m3fn",
832
+ "activations": "none"
833
+ },
834
+ "model.layers.29.mlp.up_proj": {
835
+ "weights": "qfloat8_e4m3fn",
836
+ "activations": "none"
837
+ },
838
+ "model.layers.29.mlp.down_proj": {
839
+ "weights": "qfloat8_e4m3fn",
840
+ "activations": "none"
841
+ },
842
+ "model.layers.30.self_attn.q_proj": {
843
+ "weights": "qfloat8_e4m3fn",
844
+ "activations": "none"
845
+ },
846
+ "model.layers.30.self_attn.k_proj": {
847
+ "weights": "qfloat8_e4m3fn",
848
+ "activations": "none"
849
+ },
850
+ "model.layers.30.self_attn.v_proj": {
851
+ "weights": "qfloat8_e4m3fn",
852
+ "activations": "none"
853
+ },
854
+ "model.layers.30.self_attn.o_proj": {
855
+ "weights": "qfloat8_e4m3fn",
856
+ "activations": "none"
857
+ },
858
+ "model.layers.30.mlp.gate_proj": {
859
+ "weights": "qfloat8_e4m3fn",
860
+ "activations": "none"
861
+ },
862
+ "model.layers.30.mlp.up_proj": {
863
+ "weights": "qfloat8_e4m3fn",
864
+ "activations": "none"
865
+ },
866
+ "model.layers.30.mlp.down_proj": {
867
+ "weights": "qfloat8_e4m3fn",
868
+ "activations": "none"
869
+ },
870
+ "model.layers.31.self_attn.q_proj": {
871
+ "weights": "qfloat8_e4m3fn",
872
+ "activations": "none"
873
+ },
874
+ "model.layers.31.self_attn.k_proj": {
875
+ "weights": "qfloat8_e4m3fn",
876
+ "activations": "none"
877
+ },
878
+ "model.layers.31.self_attn.v_proj": {
879
+ "weights": "qfloat8_e4m3fn",
880
+ "activations": "none"
881
+ },
882
+ "model.layers.31.self_attn.o_proj": {
883
+ "weights": "qfloat8_e4m3fn",
884
+ "activations": "none"
885
+ },
886
+ "model.layers.31.mlp.gate_proj": {
887
+ "weights": "qfloat8_e4m3fn",
888
+ "activations": "none"
889
+ },
890
+ "model.layers.31.mlp.up_proj": {
891
+ "weights": "qfloat8_e4m3fn",
892
+ "activations": "none"
893
+ },
894
+ "model.layers.31.mlp.down_proj": {
895
+ "weights": "qfloat8_e4m3fn",
896
+ "activations": "none"
897
+ },
898
+ "model.layers.32.self_attn.q_proj": {
899
+ "weights": "qfloat8_e4m3fn",
900
+ "activations": "none"
901
+ },
902
+ "model.layers.32.self_attn.k_proj": {
903
+ "weights": "qfloat8_e4m3fn",
904
+ "activations": "none"
905
+ },
906
+ "model.layers.32.self_attn.v_proj": {
907
+ "weights": "qfloat8_e4m3fn",
908
+ "activations": "none"
909
+ },
910
+ "model.layers.32.self_attn.o_proj": {
911
+ "weights": "qfloat8_e4m3fn",
912
+ "activations": "none"
913
+ },
914
+ "model.layers.32.mlp.gate_proj": {
915
+ "weights": "qfloat8_e4m3fn",
916
+ "activations": "none"
917
+ },
918
+ "model.layers.32.mlp.up_proj": {
919
+ "weights": "qfloat8_e4m3fn",
920
+ "activations": "none"
921
+ },
922
+ "model.layers.32.mlp.down_proj": {
923
+ "weights": "qfloat8_e4m3fn",
924
+ "activations": "none"
925
+ },
926
+ "model.layers.33.self_attn.q_proj": {
927
+ "weights": "qfloat8_e4m3fn",
928
+ "activations": "none"
929
+ },
930
+ "model.layers.33.self_attn.k_proj": {
931
+ "weights": "qfloat8_e4m3fn",
932
+ "activations": "none"
933
+ },
934
+ "model.layers.33.self_attn.v_proj": {
935
+ "weights": "qfloat8_e4m3fn",
936
+ "activations": "none"
937
+ },
938
+ "model.layers.33.self_attn.o_proj": {
939
+ "weights": "qfloat8_e4m3fn",
940
+ "activations": "none"
941
+ },
942
+ "model.layers.33.mlp.gate_proj": {
943
+ "weights": "qfloat8_e4m3fn",
944
+ "activations": "none"
945
+ },
946
+ "model.layers.33.mlp.up_proj": {
947
+ "weights": "qfloat8_e4m3fn",
948
+ "activations": "none"
949
+ },
950
+ "model.layers.33.mlp.down_proj": {
951
+ "weights": "qfloat8_e4m3fn",
952
+ "activations": "none"
953
+ },
954
+ "model.layers.34.self_attn.q_proj": {
955
+ "weights": "qfloat8_e4m3fn",
956
+ "activations": "none"
957
+ },
958
+ "model.layers.34.self_attn.k_proj": {
959
+ "weights": "qfloat8_e4m3fn",
960
+ "activations": "none"
961
+ },
962
+ "model.layers.34.self_attn.v_proj": {
963
+ "weights": "qfloat8_e4m3fn",
964
+ "activations": "none"
965
+ },
966
+ "model.layers.34.self_attn.o_proj": {
967
+ "weights": "qfloat8_e4m3fn",
968
+ "activations": "none"
969
+ },
970
+ "model.layers.34.mlp.gate_proj": {
971
+ "weights": "qfloat8_e4m3fn",
972
+ "activations": "none"
973
+ },
974
+ "model.layers.34.mlp.up_proj": {
975
+ "weights": "qfloat8_e4m3fn",
976
+ "activations": "none"
977
+ },
978
+ "model.layers.34.mlp.down_proj": {
979
+ "weights": "qfloat8_e4m3fn",
980
+ "activations": "none"
981
+ },
982
+ "model.layers.35.self_attn.q_proj": {
983
+ "weights": "qfloat8_e4m3fn",
984
+ "activations": "none"
985
+ },
986
+ "model.layers.35.self_attn.k_proj": {
987
+ "weights": "qfloat8_e4m3fn",
988
+ "activations": "none"
989
+ },
990
+ "model.layers.35.self_attn.v_proj": {
991
+ "weights": "qfloat8_e4m3fn",
992
+ "activations": "none"
993
+ },
994
+ "model.layers.35.self_attn.o_proj": {
995
+ "weights": "qfloat8_e4m3fn",
996
+ "activations": "none"
997
+ },
998
+ "model.layers.35.mlp.gate_proj": {
999
+ "weights": "qfloat8_e4m3fn",
1000
+ "activations": "none"
1001
+ },
1002
+ "model.layers.35.mlp.up_proj": {
1003
+ "weights": "qfloat8_e4m3fn",
1004
+ "activations": "none"
1005
+ },
1006
+ "model.layers.35.mlp.down_proj": {
1007
+ "weights": "qfloat8_e4m3fn",
1008
+ "activations": "none"
1009
+ },
1010
+ "lm_head": {
1011
+ "weights": "qfloat8_e4m3fn",
1012
+ "activations": "none"
1013
+ }
1014
+ }