nglain commited on
Commit
5ee3d83
1 Parent(s): cbcef1f

Upload folder using huggingface_hub (#5)

Browse files

- a5af8e337049f0da88800c65ae0884e2c6e174490c3e9b8cda0348f9dd354890 (bf2df07d5a6c477942b7beefee22c1c9c8b0b732)
- cee359912d537032f478bbec3e020070b3041c195e17134afaff0f5b4a084f68 (e19b16282ca048fac055c6680a1438f8b9123b7e)
- f909ec55955f074ae2c3c86d263bd75c453a8c82575cc0f9f0d2d2d45376d1d6 (b66de157b9ea92b682e9253e3f61bffa8d9fb79d)
- fb42fcc7c6ff7d52521820460643174820ec4ef92328abec9b029343c4e0f65d (ca4a7ed05a499a62bc590653705a9a6e11ac86ca)
- 62d0e23c91cf88fb7dd2fd322759d4a28a5e88aafd9d870a44af2123e952827c (6ff855ad45384a3f58f4f2fd10f43762ce4d9925)
- 6faf033890a04160a04ddd32f47142e217947959571eada441fbc6bbbe7fa02c (76559714b813deeb95563ca821c88b4dab591f72)
- 4af8246f63881fc2d6058320c88d03f2beb503f394bf5e6c6c8ab40239ad257c (cce4d8442e187ddd5c8dc67a65c90b633e3178c6)
- a830650ce805848ee20b227b0fa80d6a8cc294e56fd4dd6b9c88341d28b2977c (ed764c1a0fd18a906cf3912f65d178678d9497d8)
- 5600548831a8f68bc813d5121682a0b9d5382267758f4bf7477176dddd0d4372 (a28d516620a3f673db5171d47bde095ce2f97cfd)
- 718e4bbc9ff32f48f7390374c97b389617a1d3b29b41d0d741a0bf67d3826441 (a9c1c42a694741ecc16779a9b9a9b9fa58b30fe5)
- 2479d750a766c6f1a9d031f3a97fc2cceea231ca6886c3265523af242ea800e0 (bb3fcdc249367f39f8a8861bb687ecac36b9e189)
- 24527835c7dab1a32fa72f4a287090d72c06c61c97c601a146e7eedfd7ae692d (07d770e7bc06562eb59e475b89aa076e534d80bd)
- 656b5fdd5350bf7744c7c5a71b3876e142ed365e5d4939c51204b393dc2f77c3 (4f67dc62d7b7df222e0cd78e9de4e463f2562266)
- c0e4bb506e8f5d0a574812579660e0d5c0d1f2756263af3f6d23be7947684029 (2857d09a9f10e15729b672b30451778ac9e8427e)
- 3c741c8325a358a2dd103072f5ae59297b1cb2f12357c58ae1982d37273e7895 (09e705aed9b1c2dad5374b7cbe4c3f65fb3c340d)
- 9cd60f3f68423808e1ee62294773cd27a40705579e7fc47b03c8ddcaf6dd01fc (d1c3d5fc5f7cf9f569dc0230a8a0c3d509ff5ae0)
- ddea436fd0f5c69957ff33fcecae723148a5ba1cb2465e0643a78e3fb3cd087f (c1b78f164a92b01a52597fd26877aab2674e5c63)
- 1cf2ed424d1c61c75447950e33531a0ce1bb5790944ce763e0521730f6f7e065 (6fc171877cb4ca02ec1ab971e18535ca319420dc)
- 9e1baf10086818a749f565d729763685e8b1d3f6e8addfe9c52b7c89502fbf70 (cfdd13b5412956f1fef6501ebfc95af0a7ce381a)
- 304c633a281388aaba91f7971e882bc2408345f713ab02b7ace814d74a046e07 (5b178fcce796ddb8c9af16dac5c7819d38c93406)
- e991de6159072c6d9ddd9efae773a9541cb6ff11e93b2db7c3d404c3e90473ad (585789ac6def4738d0175bdb40685831fc58ec99)
- c901e740d036b0ca220b67c9f59bbb689a873e1c0cfba8c42a65916a20d12ac2 (88982bd89aeb244a38aa47aae604e0cd4ecd2040)
- 72e997f8f1d06eed8ba08068b82068f1ee60fb9c48a51e4cab188ac4bf1d31cf (67ac8fa4c53eaec58eda5640e8afa9ce6055b7d8)
- 827b60f15bc858080158e0963838c0305ae699d524cae57eb2bbfb77e1937662 (27fce600073b95fe1914b64be26ba8b3536679f9)
- 66a4c5a2b2fbbee9d327909c8aea4b94a417f5a837b0ea4fd8bba0b5aeb79d25 (92d39868cb35abda086c933484e0fff64fb5dda8)
- 83c089c9ff009faad9958a25f45e45333ece2f3e0a9f173641397d4237d7b281 (2922524bbda51a65fbc92d159ac49f9591ed286f)
- 129331a338e1eda72f61a6d671a2d23621637005e4dc158b62ee8e823e6591d0 (41f7f8b60712984dd13ddb55cb61a97f7a6e5849)
- b712ad6b33c22ffa3bc81b00a29a2b8ae25280311632a3598b1e3935276abd70 (04cfe4c1ba11c4616a4694c00b8a3587945bc779)
- 58c0878b512509f83146f0214b7bad138aadce9ea3f81d4fb19ad0d5eb277c60 (67137c465f4c3485bdfbf23345576c9ca0be8502)
- c4a7259f7b8261bbca41fcfb610eb121a9dd8309661e6c8c17434130d81d783d (fd6a67b941f79bbff3423525b340c37d41a4b23d)
- bed21086d2d008b7595c8ab2a023c0fe1ce05f3f838009906981c90fe62b4ae7 (e70066fe047aaf5f5fbe807ea9a1062962596115)
- 0464e2438a31c2f9979a1f0d6d2318bf2a48af5db2668fb657803a56696c3a7a (519bdb5111557b3196c76fe638a3d078e0d427af)
- c6e3ff395ae3c62ea5581c236bc374d9eae5f4889cb4354baed8648ab24a35d6 (b9af53096705ac1660b0331ca6aca77804a1e24e)
- c7a5adb3bc691df481e6b90afc58399fcda35784f83cb39d31e6cfbe5439df90 (69d1aa28ffc1b87f5930b6ee6b4503c9cc7ab65d)
- 951f9bbffa50258a2c204033d30535d96af6d2f461c2fcf5d2fc82df5e0fa257 (ad69e6f979953cd53c9c719dc9b18d11569814b6)
- 1b5910a06ae612dea46dfe045b8591b4907441a341e8132df050f3ed9d5dad78 (dbc62a1d4a9febba760581572b3a34eac35a1327)
- e82fe47eafe6bf708aac39a96f3a1f917bc6785a745ce40aa347373cff74dfba (6bfda03fc6eb3420428a8ec62f27daf8bd84a9fc)
- 9cb84680659125150bf38478a4ef3c712d091ed9142d3ef8c25600713ed3217e (a225a1eb6c54a02b0738e10bc24870501ecea3d6)
- 6a9b19e153f751fa38026fd3b37fd2847911135b560790c618b45d5c44d98ae4 (57f3d8b6893313eebe4337331649d1e2ac871121)

.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
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
+
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]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
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
+
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]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/workspace/text-generation-webui/models/Mixtral-8x7B-Instruct-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "o_proj",
25
+ "v_proj",
26
+ "k_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac6916311062c254ed0ae61af2d645b641c4db57f23853af81ba6d829a44b98
3
+ size 109086672
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/text-generation-webui/models/Mixtral-8x7B-Instruct-v0.1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.41.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.41.1"
6
+ }
model-00039-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858d561f1f8420b5d8ec4532cec32abb5f6cbf7fbf06ff736190a8a9ebb7546c
3
+ size 1463862216
model.safetensors.index.json ADDED
@@ -0,0 +1,1002 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 186811170816
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00039-of-00039.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00039.safetensors",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00039.safetensors",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00039.safetensors",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00039.safetensors",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00039.safetensors",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00039.safetensors",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00039.safetensors",
14
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00039.safetensors",
15
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00039.safetensors",
16
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00039.safetensors",
17
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00039.safetensors",
18
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00039.safetensors",
19
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00039.safetensors",
20
+ "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00039.safetensors",
21
+ "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00039.safetensors",
22
+ "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00039.safetensors",
23
+ "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00039.safetensors",
24
+ "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00039.safetensors",
25
+ "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00039.safetensors",
26
+ "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00039.safetensors",
27
+ "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00039.safetensors",
28
+ "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00039.safetensors",
29
+ "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00039.safetensors",
30
+ "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00039.safetensors",
31
+ "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00039.safetensors",
32
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00039.safetensors",
33
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00039.safetensors",
34
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00039.safetensors",
35
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00039.safetensors",
36
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00039.safetensors",
37
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00039.safetensors",
38
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00039.safetensors",
39
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00039.safetensors",
40
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00039.safetensors",
41
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00039.safetensors",
42
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00039.safetensors",
43
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00039.safetensors",
44
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00039.safetensors",
45
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00039.safetensors",
46
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00039.safetensors",
47
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00039.safetensors",
48
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00039.safetensors",
49
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00039.safetensors",
50
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00039.safetensors",
51
+ "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00039.safetensors",
52
+ "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00039.safetensors",
53
+ "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00039.safetensors",
54
+ "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00039.safetensors",
55
+ "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00039.safetensors",
56
+ "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00039.safetensors",
57
+ "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00039.safetensors",
58
+ "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00039.safetensors",
59
+ "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00039.safetensors",
60
+ "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00039.safetensors",
61
+ "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00039.safetensors",
62
+ "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00039.safetensors",
63
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00039.safetensors",
64
+ "model.layers.1.input_layernorm.weight": "model-00003-of-00039.safetensors",
65
+ "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00039.safetensors",
66
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00039.safetensors",
67
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00039.safetensors",
68
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00039.safetensors",
69
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00039.safetensors",
70
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00039.safetensors",
71
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00039.safetensors",
72
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00039.safetensors",
73
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00039.safetensors",
74
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00039.safetensors",
75
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00039.safetensors",
76
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00039.safetensors",
77
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00039.safetensors",
78
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00039.safetensors",
79
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00039.safetensors",
80
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00039.safetensors",
81
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00039.safetensors",
82
+ "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00039.safetensors",
83
+ "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00039.safetensors",
84
+ "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00039.safetensors",
85
+ "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00039.safetensors",
86
+ "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00039.safetensors",
87
+ "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00039.safetensors",
88
+ "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00039.safetensors",
89
+ "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00039.safetensors",
90
+ "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00039.safetensors",
91
+ "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00039.safetensors",
92
+ "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00039.safetensors",
93
+ "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00039.safetensors",
94
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00039.safetensors",
95
+ "model.layers.10.input_layernorm.weight": "model-00014-of-00039.safetensors",
96
+ "model.layers.10.post_attention_layernorm.weight": "model-00014-of-00039.safetensors",
97
+ "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00039.safetensors",
98
+ "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00039.safetensors",
99
+ "model.layers.10.self_attn.q_proj.weight": "model-00012-of-00039.safetensors",
100
+ "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00039.safetensors",
101
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00039.safetensors",
102
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00039.safetensors",
103
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00039.safetensors",
104
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00039.safetensors",
105
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00039.safetensors",
106
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00039.safetensors",
107
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00039.safetensors",
108
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00039.safetensors",
109
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00039.safetensors",
110
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00039.safetensors",
111
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00039.safetensors",
112
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00039.safetensors",
113
+ "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00039.safetensors",
114
+ "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00039.safetensors",
115
+ "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00039.safetensors",
116
+ "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00039.safetensors",
117
+ "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00039.safetensors",
118
+ "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00039.safetensors",
119
+ "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00039.safetensors",
120
+ "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00039.safetensors",
121
+ "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00039.safetensors",
122
+ "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00039.safetensors",
123
+ "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00039.safetensors",
124
+ "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00039.safetensors",
125
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00014-of-00039.safetensors",
126
+ "model.layers.11.input_layernorm.weight": "model-00015-of-00039.safetensors",
127
+ "model.layers.11.post_attention_layernorm.weight": "model-00015-of-00039.safetensors",
128
+ "model.layers.11.self_attn.k_proj.weight": "model-00014-of-00039.safetensors",
129
+ "model.layers.11.self_attn.o_proj.weight": "model-00014-of-00039.safetensors",
130
+ "model.layers.11.self_attn.q_proj.weight": "model-00014-of-00039.safetensors",
131
+ "model.layers.11.self_attn.v_proj.weight": "model-00014-of-00039.safetensors",
132
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00039.safetensors",
133
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00039.safetensors",
134
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00039.safetensors",
135
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00039.safetensors",
136
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00039.safetensors",
137
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00039.safetensors",
138
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00039.safetensors",
139
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00039.safetensors",
140
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00039.safetensors",
141
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00039.safetensors",
142
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00039.safetensors",
143
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00039.safetensors",
144
+ "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00039.safetensors",
145
+ "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00039.safetensors",
146
+ "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00039.safetensors",
147
+ "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00039.safetensors",
148
+ "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00039.safetensors",
149
+ "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00039.safetensors",
150
+ "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00039.safetensors",
151
+ "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00039.safetensors",
152
+ "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00039.safetensors",
153
+ "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00039.safetensors",
154
+ "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00039.safetensors",
155
+ "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00039.safetensors",
156
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00015-of-00039.safetensors",
157
+ "model.layers.12.input_layernorm.weight": "model-00016-of-00039.safetensors",
158
+ "model.layers.12.post_attention_layernorm.weight": "model-00016-of-00039.safetensors",
159
+ "model.layers.12.self_attn.k_proj.weight": "model-00015-of-00039.safetensors",
160
+ "model.layers.12.self_attn.o_proj.weight": "model-00015-of-00039.safetensors",
161
+ "model.layers.12.self_attn.q_proj.weight": "model-00015-of-00039.safetensors",
162
+ "model.layers.12.self_attn.v_proj.weight": "model-00015-of-00039.safetensors",
163
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00039.safetensors",
164
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00039.safetensors",
165
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00039.safetensors",
166
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00039.safetensors",
167
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00039.safetensors",
168
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00039.safetensors",
169
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00039.safetensors",
170
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00039.safetensors",
171
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00039.safetensors",
172
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00039.safetensors",
173
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00039.safetensors",
174
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00039.safetensors",
175
+ "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00039.safetensors",
176
+ "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00039.safetensors",
177
+ "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00039.safetensors",
178
+ "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00039.safetensors",
179
+ "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00039.safetensors",
180
+ "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00039.safetensors",
181
+ "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00039.safetensors",
182
+ "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00039.safetensors",
183
+ "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00039.safetensors",
184
+ "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00039.safetensors",
185
+ "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00039.safetensors",
186
+ "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00039.safetensors",
187
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00016-of-00039.safetensors",
188
+ "model.layers.13.input_layernorm.weight": "model-00017-of-00039.safetensors",
189
+ "model.layers.13.post_attention_layernorm.weight": "model-00017-of-00039.safetensors",
190
+ "model.layers.13.self_attn.k_proj.weight": "model-00016-of-00039.safetensors",
191
+ "model.layers.13.self_attn.o_proj.weight": "model-00016-of-00039.safetensors",
192
+ "model.layers.13.self_attn.q_proj.weight": "model-00016-of-00039.safetensors",
193
+ "model.layers.13.self_attn.v_proj.weight": "model-00016-of-00039.safetensors",
194
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00039.safetensors",
195
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00039.safetensors",
196
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00039.safetensors",
197
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00039.safetensors",
198
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00039.safetensors",
199
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00039.safetensors",
200
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00039.safetensors",
201
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00039.safetensors",
202
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00039.safetensors",
203
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00039.safetensors",
204
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00039.safetensors",
205
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00039.safetensors",
206
+ "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00039.safetensors",
207
+ "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00039.safetensors",
208
+ "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00039.safetensors",
209
+ "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00039.safetensors",
210
+ "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00039.safetensors",
211
+ "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00039.safetensors",
212
+ "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00039.safetensors",
213
+ "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00039.safetensors",
214
+ "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00039.safetensors",
215
+ "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00039.safetensors",
216
+ "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00039.safetensors",
217
+ "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00039.safetensors",
218
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00017-of-00039.safetensors",
219
+ "model.layers.14.input_layernorm.weight": "model-00018-of-00039.safetensors",
220
+ "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00039.safetensors",
221
+ "model.layers.14.self_attn.k_proj.weight": "model-00017-of-00039.safetensors",
222
+ "model.layers.14.self_attn.o_proj.weight": "model-00017-of-00039.safetensors",
223
+ "model.layers.14.self_attn.q_proj.weight": "model-00017-of-00039.safetensors",
224
+ "model.layers.14.self_attn.v_proj.weight": "model-00017-of-00039.safetensors",
225
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00039.safetensors",
226
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00039.safetensors",
227
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00039.safetensors",
228
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00039.safetensors",
229
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00039.safetensors",
230
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00039.safetensors",
231
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00039.safetensors",
232
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00039.safetensors",
233
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00039.safetensors",
234
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00039.safetensors",
235
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00039.safetensors",
236
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00039.safetensors",
237
+ "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00039.safetensors",
238
+ "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00039.safetensors",
239
+ "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00039.safetensors",
240
+ "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00039.safetensors",
241
+ "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00039.safetensors",
242
+ "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00039.safetensors",
243
+ "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00039.safetensors",
244
+ "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00039.safetensors",
245
+ "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00039.safetensors",
246
+ "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00039.safetensors",
247
+ "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00039.safetensors",
248
+ "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00039.safetensors",
249
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00018-of-00039.safetensors",
250
+ "model.layers.15.input_layernorm.weight": "model-00020-of-00039.safetensors",
251
+ "model.layers.15.post_attention_layernorm.weight": "model-00020-of-00039.safetensors",
252
+ "model.layers.15.self_attn.k_proj.weight": "model-00018-of-00039.safetensors",
253
+ "model.layers.15.self_attn.o_proj.weight": "model-00018-of-00039.safetensors",
254
+ "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00039.safetensors",
255
+ "model.layers.15.self_attn.v_proj.weight": "model-00018-of-00039.safetensors",
256
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00039.safetensors",
257
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00039.safetensors",
258
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00039.safetensors",
259
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00039.safetensors",
260
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00039.safetensors",
261
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00039.safetensors",
262
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00039.safetensors",
263
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00039.safetensors",
264
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00039.safetensors",
265
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00039.safetensors",
266
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00039.safetensors",
267
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00039.safetensors",
268
+ "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00039.safetensors",
269
+ "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00039.safetensors",
270
+ "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00039.safetensors",
271
+ "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00039.safetensors",
272
+ "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00039.safetensors",
273
+ "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00039.safetensors",
274
+ "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00039.safetensors",
275
+ "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00039.safetensors",
276
+ "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00039.safetensors",
277
+ "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00039.safetensors",
278
+ "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00039.safetensors",
279
+ "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00039.safetensors",
280
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00020-of-00039.safetensors",
281
+ "model.layers.16.input_layernorm.weight": "model-00021-of-00039.safetensors",
282
+ "model.layers.16.post_attention_layernorm.weight": "model-00021-of-00039.safetensors",
283
+ "model.layers.16.self_attn.k_proj.weight": "model-00020-of-00039.safetensors",
284
+ "model.layers.16.self_attn.o_proj.weight": "model-00020-of-00039.safetensors",
285
+ "model.layers.16.self_attn.q_proj.weight": "model-00020-of-00039.safetensors",
286
+ "model.layers.16.self_attn.v_proj.weight": "model-00020-of-00039.safetensors",
287
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00039.safetensors",
288
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00039.safetensors",
289
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00039.safetensors",
290
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00039.safetensors",
291
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00039.safetensors",
292
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00039.safetensors",
293
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00039.safetensors",
294
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00039.safetensors",
295
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00039.safetensors",
296
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00039.safetensors",
297
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00039.safetensors",
298
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00039.safetensors",
299
+ "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00039.safetensors",
300
+ "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00039.safetensors",
301
+ "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00039.safetensors",
302
+ "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00039.safetensors",
303
+ "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00039.safetensors",
304
+ "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00039.safetensors",
305
+ "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00022-of-00039.safetensors",
306
+ "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00039.safetensors",
307
+ "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00039.safetensors",
308
+ "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00039.safetensors",
309
+ "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00039.safetensors",
310
+ "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00039.safetensors",
311
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00021-of-00039.safetensors",
312
+ "model.layers.17.input_layernorm.weight": "model-00022-of-00039.safetensors",
313
+ "model.layers.17.post_attention_layernorm.weight": "model-00022-of-00039.safetensors",
314
+ "model.layers.17.self_attn.k_proj.weight": "model-00021-of-00039.safetensors",
315
+ "model.layers.17.self_attn.o_proj.weight": "model-00021-of-00039.safetensors",
316
+ "model.layers.17.self_attn.q_proj.weight": "model-00021-of-00039.safetensors",
317
+ "model.layers.17.self_attn.v_proj.weight": "model-00021-of-00039.safetensors",
318
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00039.safetensors",
319
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00039.safetensors",
320
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00039.safetensors",
321
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00039.safetensors",
322
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00039.safetensors",
323
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00039.safetensors",
324
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00039.safetensors",
325
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00039.safetensors",
326
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00039.safetensors",
327
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00039.safetensors",
328
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00039.safetensors",
329
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00039.safetensors",
330
+ "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00039.safetensors",
331
+ "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00039.safetensors",
332
+ "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00039.safetensors",
333
+ "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00039.safetensors",
334
+ "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00039.safetensors",
335
+ "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00039.safetensors",
336
+ "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00039.safetensors",
337
+ "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00039.safetensors",
338
+ "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00039.safetensors",
339
+ "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00039.safetensors",
340
+ "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00039.safetensors",
341
+ "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00039.safetensors",
342
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00022-of-00039.safetensors",
343
+ "model.layers.18.input_layernorm.weight": "model-00023-of-00039.safetensors",
344
+ "model.layers.18.post_attention_layernorm.weight": "model-00023-of-00039.safetensors",
345
+ "model.layers.18.self_attn.k_proj.weight": "model-00022-of-00039.safetensors",
346
+ "model.layers.18.self_attn.o_proj.weight": "model-00022-of-00039.safetensors",
347
+ "model.layers.18.self_attn.q_proj.weight": "model-00022-of-00039.safetensors",
348
+ "model.layers.18.self_attn.v_proj.weight": "model-00022-of-00039.safetensors",
349
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00039.safetensors",
350
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00039.safetensors",
351
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00039.safetensors",
352
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00039.safetensors",
353
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00039.safetensors",
354
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00039.safetensors",
355
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00039.safetensors",
356
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00039.safetensors",
357
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00039.safetensors",
358
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00039.safetensors",
359
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00039.safetensors",
360
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00039.safetensors",
361
+ "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00039.safetensors",
362
+ "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00039.safetensors",
363
+ "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00039.safetensors",
364
+ "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00039.safetensors",
365
+ "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00039.safetensors",
366
+ "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00039.safetensors",
367
+ "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00039.safetensors",
368
+ "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00039.safetensors",
369
+ "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00039.safetensors",
370
+ "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00039.safetensors",
371
+ "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00039.safetensors",
372
+ "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00039.safetensors",
373
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00023-of-00039.safetensors",
374
+ "model.layers.19.input_layernorm.weight": "model-00024-of-00039.safetensors",
375
+ "model.layers.19.post_attention_layernorm.weight": "model-00024-of-00039.safetensors",
376
+ "model.layers.19.self_attn.k_proj.weight": "model-00023-of-00039.safetensors",
377
+ "model.layers.19.self_attn.o_proj.weight": "model-00023-of-00039.safetensors",
378
+ "model.layers.19.self_attn.q_proj.weight": "model-00023-of-00039.safetensors",
379
+ "model.layers.19.self_attn.v_proj.weight": "model-00023-of-00039.safetensors",
380
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00039.safetensors",
381
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00039.safetensors",
382
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00039.safetensors",
383
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00039.safetensors",
384
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00039.safetensors",
385
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00039.safetensors",
386
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00039.safetensors",
387
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00039.safetensors",
388
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00039.safetensors",
389
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00039.safetensors",
390
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00039.safetensors",
391
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00039.safetensors",
392
+ "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00039.safetensors",
393
+ "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00039.safetensors",
394
+ "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00039.safetensors",
395
+ "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00039.safetensors",
396
+ "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00039.safetensors",
397
+ "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00039.safetensors",
398
+ "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00039.safetensors",
399
+ "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00039.safetensors",
400
+ "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00039.safetensors",
401
+ "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00039.safetensors",
402
+ "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00039.safetensors",
403
+ "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00039.safetensors",
404
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00039.safetensors",
405
+ "model.layers.2.input_layernorm.weight": "model-00004-of-00039.safetensors",
406
+ "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00039.safetensors",
407
+ "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00039.safetensors",
408
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00039.safetensors",
409
+ "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00039.safetensors",
410
+ "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00039.safetensors",
411
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00039.safetensors",
412
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00039.safetensors",
413
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00039.safetensors",
414
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00039.safetensors",
415
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00039.safetensors",
416
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00039.safetensors",
417
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00039.safetensors",
418
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00039.safetensors",
419
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00039.safetensors",
420
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00039.safetensors",
421
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00039.safetensors",
422
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00039.safetensors",
423
+ "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00039.safetensors",
424
+ "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00039.safetensors",
425
+ "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00039.safetensors",
426
+ "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00039.safetensors",
427
+ "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00039.safetensors",
428
+ "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00039.safetensors",
429
+ "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00039.safetensors",
430
+ "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00039.safetensors",
431
+ "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00039.safetensors",
432
+ "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00039.safetensors",
433
+ "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00039.safetensors",
434
+ "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00039.safetensors",
435
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00024-of-00039.safetensors",
436
+ "model.layers.20.input_layernorm.weight": "model-00026-of-00039.safetensors",
437
+ "model.layers.20.post_attention_layernorm.weight": "model-00026-of-00039.safetensors",
438
+ "model.layers.20.self_attn.k_proj.weight": "model-00024-of-00039.safetensors",
439
+ "model.layers.20.self_attn.o_proj.weight": "model-00024-of-00039.safetensors",
440
+ "model.layers.20.self_attn.q_proj.weight": "model-00024-of-00039.safetensors",
441
+ "model.layers.20.self_attn.v_proj.weight": "model-00024-of-00039.safetensors",
442
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00039.safetensors",
443
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00039.safetensors",
444
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00039.safetensors",
445
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00039.safetensors",
446
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00039.safetensors",
447
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00039.safetensors",
448
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00039.safetensors",
449
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00039.safetensors",
450
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00039.safetensors",
451
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00039.safetensors",
452
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00039.safetensors",
453
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00039.safetensors",
454
+ "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00039.safetensors",
455
+ "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00039.safetensors",
456
+ "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00039.safetensors",
457
+ "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00039.safetensors",
458
+ "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00039.safetensors",
459
+ "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00039.safetensors",
460
+ "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00039.safetensors",
461
+ "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00039.safetensors",
462
+ "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00039.safetensors",
463
+ "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00039.safetensors",
464
+ "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00039.safetensors",
465
+ "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00039.safetensors",
466
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00026-of-00039.safetensors",
467
+ "model.layers.21.input_layernorm.weight": "model-00027-of-00039.safetensors",
468
+ "model.layers.21.post_attention_layernorm.weight": "model-00027-of-00039.safetensors",
469
+ "model.layers.21.self_attn.k_proj.weight": "model-00026-of-00039.safetensors",
470
+ "model.layers.21.self_attn.o_proj.weight": "model-00026-of-00039.safetensors",
471
+ "model.layers.21.self_attn.q_proj.weight": "model-00026-of-00039.safetensors",
472
+ "model.layers.21.self_attn.v_proj.weight": "model-00026-of-00039.safetensors",
473
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00039.safetensors",
474
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00039.safetensors",
475
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00039.safetensors",
476
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00039.safetensors",
477
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00039.safetensors",
478
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00039.safetensors",
479
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00039.safetensors",
480
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00039.safetensors",
481
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00039.safetensors",
482
+ "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00039.safetensors",
483
+ "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00039.safetensors",
484
+ "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00039.safetensors",
485
+ "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00039.safetensors",
486
+ "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00039.safetensors",
487
+ "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00039.safetensors",
488
+ "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00039.safetensors",
489
+ "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00039.safetensors",
490
+ "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00039.safetensors",
491
+ "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00039.safetensors",
492
+ "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00039.safetensors",
493
+ "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00039.safetensors",
494
+ "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00039.safetensors",
495
+ "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00039.safetensors",
496
+ "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00039.safetensors",
497
+ "model.layers.22.block_sparse_moe.gate.weight": "model-00027-of-00039.safetensors",
498
+ "model.layers.22.input_layernorm.weight": "model-00028-of-00039.safetensors",
499
+ "model.layers.22.post_attention_layernorm.weight": "model-00028-of-00039.safetensors",
500
+ "model.layers.22.self_attn.k_proj.weight": "model-00027-of-00039.safetensors",
501
+ "model.layers.22.self_attn.o_proj.weight": "model-00027-of-00039.safetensors",
502
+ "model.layers.22.self_attn.q_proj.weight": "model-00027-of-00039.safetensors",
503
+ "model.layers.22.self_attn.v_proj.weight": "model-00027-of-00039.safetensors",
504
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00039.safetensors",
505
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00039.safetensors",
506
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00039.safetensors",
507
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00039.safetensors",
508
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00039.safetensors",
509
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00039.safetensors",
510
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00039.safetensors",
511
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00039.safetensors",
512
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00039.safetensors",
513
+ "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00039.safetensors",
514
+ "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00039.safetensors",
515
+ "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00039.safetensors",
516
+ "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00039.safetensors",
517
+ "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00039.safetensors",
518
+ "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00039.safetensors",
519
+ "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00039.safetensors",
520
+ "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00039.safetensors",
521
+ "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00039.safetensors",
522
+ "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00039.safetensors",
523
+ "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00039.safetensors",
524
+ "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00039.safetensors",
525
+ "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00039.safetensors",
526
+ "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00039.safetensors",
527
+ "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00039.safetensors",
528
+ "model.layers.23.block_sparse_moe.gate.weight": "model-00028-of-00039.safetensors",
529
+ "model.layers.23.input_layernorm.weight": "model-00029-of-00039.safetensors",
530
+ "model.layers.23.post_attention_layernorm.weight": "model-00029-of-00039.safetensors",
531
+ "model.layers.23.self_attn.k_proj.weight": "model-00028-of-00039.safetensors",
532
+ "model.layers.23.self_attn.o_proj.weight": "model-00028-of-00039.safetensors",
533
+ "model.layers.23.self_attn.q_proj.weight": "model-00028-of-00039.safetensors",
534
+ "model.layers.23.self_attn.v_proj.weight": "model-00028-of-00039.safetensors",
535
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00039.safetensors",
536
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00039.safetensors",
537
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00039.safetensors",
538
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00039.safetensors",
539
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00039.safetensors",
540
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00039.safetensors",
541
+ "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00039.safetensors",
542
+ "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00039.safetensors",
543
+ "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00039.safetensors",
544
+ "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00039.safetensors",
545
+ "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00039.safetensors",
546
+ "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00039.safetensors",
547
+ "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00039.safetensors",
548
+ "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00039.safetensors",
549
+ "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00039.safetensors",
550
+ "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00039.safetensors",
551
+ "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00039.safetensors",
552
+ "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00039.safetensors",
553
+ "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00039.safetensors",
554
+ "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00039.safetensors",
555
+ "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00039.safetensors",
556
+ "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00039.safetensors",
557
+ "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00039.safetensors",
558
+ "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00039.safetensors",
559
+ "model.layers.24.block_sparse_moe.gate.weight": "model-00029-of-00039.safetensors",
560
+ "model.layers.24.input_layernorm.weight": "model-00030-of-00039.safetensors",
561
+ "model.layers.24.post_attention_layernorm.weight": "model-00030-of-00039.safetensors",
562
+ "model.layers.24.self_attn.k_proj.weight": "model-00029-of-00039.safetensors",
563
+ "model.layers.24.self_attn.o_proj.weight": "model-00029-of-00039.safetensors",
564
+ "model.layers.24.self_attn.q_proj.weight": "model-00029-of-00039.safetensors",
565
+ "model.layers.24.self_attn.v_proj.weight": "model-00029-of-00039.safetensors",
566
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00039.safetensors",
567
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00039.safetensors",
568
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00039.safetensors",
569
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00039.safetensors",
570
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00039.safetensors",
571
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00039.safetensors",
572
+ "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00039.safetensors",
573
+ "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00039.safetensors",
574
+ "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00039.safetensors",
575
+ "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00039.safetensors",
576
+ "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00039.safetensors",
577
+ "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00039.safetensors",
578
+ "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00039.safetensors",
579
+ "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00039.safetensors",
580
+ "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00039.safetensors",
581
+ "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00039.safetensors",
582
+ "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00039.safetensors",
583
+ "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00039.safetensors",
584
+ "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00039.safetensors",
585
+ "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00039.safetensors",
586
+ "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00039.safetensors",
587
+ "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00039.safetensors",
588
+ "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00039.safetensors",
589
+ "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00039.safetensors",
590
+ "model.layers.25.block_sparse_moe.gate.weight": "model-00030-of-00039.safetensors",
591
+ "model.layers.25.input_layernorm.weight": "model-00032-of-00039.safetensors",
592
+ "model.layers.25.post_attention_layernorm.weight": "model-00032-of-00039.safetensors",
593
+ "model.layers.25.self_attn.k_proj.weight": "model-00030-of-00039.safetensors",
594
+ "model.layers.25.self_attn.o_proj.weight": "model-00030-of-00039.safetensors",
595
+ "model.layers.25.self_attn.q_proj.weight": "model-00030-of-00039.safetensors",
596
+ "model.layers.25.self_attn.v_proj.weight": "model-00030-of-00039.safetensors",
597
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00039.safetensors",
598
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00039.safetensors",
599
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00039.safetensors",
600
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00039.safetensors",
601
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00039.safetensors",
602
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00039.safetensors",
603
+ "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00039.safetensors",
604
+ "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00039.safetensors",
605
+ "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00039.safetensors",
606
+ "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00039.safetensors",
607
+ "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00039.safetensors",
608
+ "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00039.safetensors",
609
+ "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00039.safetensors",
610
+ "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00039.safetensors",
611
+ "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00039.safetensors",
612
+ "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00039.safetensors",
613
+ "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00039.safetensors",
614
+ "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00039.safetensors",
615
+ "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00039.safetensors",
616
+ "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00039.safetensors",
617
+ "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00039.safetensors",
618
+ "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00039.safetensors",
619
+ "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00039.safetensors",
620
+ "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00039.safetensors",
621
+ "model.layers.26.block_sparse_moe.gate.weight": "model-00032-of-00039.safetensors",
622
+ "model.layers.26.input_layernorm.weight": "model-00033-of-00039.safetensors",
623
+ "model.layers.26.post_attention_layernorm.weight": "model-00033-of-00039.safetensors",
624
+ "model.layers.26.self_attn.k_proj.weight": "model-00032-of-00039.safetensors",
625
+ "model.layers.26.self_attn.o_proj.weight": "model-00032-of-00039.safetensors",
626
+ "model.layers.26.self_attn.q_proj.weight": "model-00032-of-00039.safetensors",
627
+ "model.layers.26.self_attn.v_proj.weight": "model-00032-of-00039.safetensors",
628
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00039.safetensors",
629
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00039.safetensors",
630
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00039.safetensors",
631
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00039.safetensors",
632
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00039.safetensors",
633
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00039.safetensors",
634
+ "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00039.safetensors",
635
+ "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00039.safetensors",
636
+ "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00039.safetensors",
637
+ "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00039.safetensors",
638
+ "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00039.safetensors",
639
+ "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00039.safetensors",
640
+ "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00039.safetensors",
641
+ "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00039.safetensors",
642
+ "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00039.safetensors",
643
+ "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00039.safetensors",
644
+ "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00039.safetensors",
645
+ "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00039.safetensors",
646
+ "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00039.safetensors",
647
+ "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00039.safetensors",
648
+ "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00039.safetensors",
649
+ "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00039.safetensors",
650
+ "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00039.safetensors",
651
+ "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00039.safetensors",
652
+ "model.layers.27.block_sparse_moe.gate.weight": "model-00033-of-00039.safetensors",
653
+ "model.layers.27.input_layernorm.weight": "model-00034-of-00039.safetensors",
654
+ "model.layers.27.post_attention_layernorm.weight": "model-00034-of-00039.safetensors",
655
+ "model.layers.27.self_attn.k_proj.weight": "model-00033-of-00039.safetensors",
656
+ "model.layers.27.self_attn.o_proj.weight": "model-00033-of-00039.safetensors",
657
+ "model.layers.27.self_attn.q_proj.weight": "model-00033-of-00039.safetensors",
658
+ "model.layers.27.self_attn.v_proj.weight": "model-00033-of-00039.safetensors",
659
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00039.safetensors",
660
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00039.safetensors",
661
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00039.safetensors",
662
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00039.safetensors",
663
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00039.safetensors",
664
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00039.safetensors",
665
+ "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00039.safetensors",
666
+ "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00039.safetensors",
667
+ "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00039.safetensors",
668
+ "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00039.safetensors",
669
+ "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00039.safetensors",
670
+ "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00039.safetensors",
671
+ "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00039.safetensors",
672
+ "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00039.safetensors",
673
+ "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00039.safetensors",
674
+ "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00039.safetensors",
675
+ "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00039.safetensors",
676
+ "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00039.safetensors",
677
+ "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00039.safetensors",
678
+ "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00039.safetensors",
679
+ "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00039.safetensors",
680
+ "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00039.safetensors",
681
+ "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00039.safetensors",
682
+ "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00039.safetensors",
683
+ "model.layers.28.block_sparse_moe.gate.weight": "model-00034-of-00039.safetensors",
684
+ "model.layers.28.input_layernorm.weight": "model-00035-of-00039.safetensors",
685
+ "model.layers.28.post_attention_layernorm.weight": "model-00035-of-00039.safetensors",
686
+ "model.layers.28.self_attn.k_proj.weight": "model-00034-of-00039.safetensors",
687
+ "model.layers.28.self_attn.o_proj.weight": "model-00034-of-00039.safetensors",
688
+ "model.layers.28.self_attn.q_proj.weight": "model-00034-of-00039.safetensors",
689
+ "model.layers.28.self_attn.v_proj.weight": "model-00034-of-00039.safetensors",
690
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00039.safetensors",
691
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00039.safetensors",
692
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00039.safetensors",
693
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00039.safetensors",
694
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00039.safetensors",
695
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00039.safetensors",
696
+ "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00039.safetensors",
697
+ "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00039.safetensors",
698
+ "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00039.safetensors",
699
+ "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00039.safetensors",
700
+ "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00039.safetensors",
701
+ "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00039.safetensors",
702
+ "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00039.safetensors",
703
+ "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00039.safetensors",
704
+ "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00039.safetensors",
705
+ "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00039.safetensors",
706
+ "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00039.safetensors",
707
+ "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00039.safetensors",
708
+ "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00039.safetensors",
709
+ "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00039.safetensors",
710
+ "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00039.safetensors",
711
+ "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00039.safetensors",
712
+ "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00039.safetensors",
713
+ "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00039.safetensors",
714
+ "model.layers.29.block_sparse_moe.gate.weight": "model-00035-of-00039.safetensors",
715
+ "model.layers.29.input_layernorm.weight": "model-00036-of-00039.safetensors",
716
+ "model.layers.29.post_attention_layernorm.weight": "model-00036-of-00039.safetensors",
717
+ "model.layers.29.self_attn.k_proj.weight": "model-00035-of-00039.safetensors",
718
+ "model.layers.29.self_attn.o_proj.weight": "model-00035-of-00039.safetensors",
719
+ "model.layers.29.self_attn.q_proj.weight": "model-00035-of-00039.safetensors",
720
+ "model.layers.29.self_attn.v_proj.weight": "model-00035-of-00039.safetensors",
721
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00039.safetensors",
722
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00039.safetensors",
723
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00039.safetensors",
724
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00039.safetensors",
725
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00039.safetensors",
726
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00039.safetensors",
727
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00039.safetensors",
728
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00039.safetensors",
729
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00039.safetensors",
730
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00039.safetensors",
731
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00039.safetensors",
732
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00039.safetensors",
733
+ "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00039.safetensors",
734
+ "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00039.safetensors",
735
+ "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00039.safetensors",
736
+ "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00039.safetensors",
737
+ "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00039.safetensors",
738
+ "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00039.safetensors",
739
+ "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00039.safetensors",
740
+ "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00039.safetensors",
741
+ "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00039.safetensors",
742
+ "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00039.safetensors",
743
+ "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00039.safetensors",
744
+ "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00039.safetensors",
745
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00039.safetensors",
746
+ "model.layers.3.input_layernorm.weight": "model-00005-of-00039.safetensors",
747
+ "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00039.safetensors",
748
+ "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00039.safetensors",
749
+ "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00039.safetensors",
750
+ "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00039.safetensors",
751
+ "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00039.safetensors",
752
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00039.safetensors",
753
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00039.safetensors",
754
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00039.safetensors",
755
+ "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00039.safetensors",
756
+ "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00039.safetensors",
757
+ "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00039.safetensors",
758
+ "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00039.safetensors",
759
+ "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00039.safetensors",
760
+ "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00039.safetensors",
761
+ "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00039.safetensors",
762
+ "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00039.safetensors",
763
+ "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00039.safetensors",
764
+ "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00039.safetensors",
765
+ "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00039.safetensors",
766
+ "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00039.safetensors",
767
+ "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00039.safetensors",
768
+ "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00039.safetensors",
769
+ "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00039.safetensors",
770
+ "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00039.safetensors",
771
+ "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00039.safetensors",
772
+ "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00039.safetensors",
773
+ "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00039.safetensors",
774
+ "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00039.safetensors",
775
+ "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00039.safetensors",
776
+ "model.layers.30.block_sparse_moe.gate.weight": "model-00036-of-00039.safetensors",
777
+ "model.layers.30.input_layernorm.weight": "model-00037-of-00039.safetensors",
778
+ "model.layers.30.post_attention_layernorm.weight": "model-00037-of-00039.safetensors",
779
+ "model.layers.30.self_attn.k_proj.weight": "model-00036-of-00039.safetensors",
780
+ "model.layers.30.self_attn.o_proj.weight": "model-00036-of-00039.safetensors",
781
+ "model.layers.30.self_attn.q_proj.weight": "model-00036-of-00039.safetensors",
782
+ "model.layers.30.self_attn.v_proj.weight": "model-00036-of-00039.safetensors",
783
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00039.safetensors",
784
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00039.safetensors",
785
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00039.safetensors",
786
+ "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00039.safetensors",
787
+ "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00039.safetensors",
788
+ "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00039.safetensors",
789
+ "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00039.safetensors",
790
+ "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00039.safetensors",
791
+ "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00039.safetensors",
792
+ "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00039.safetensors",
793
+ "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00039.safetensors",
794
+ "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00039.safetensors",
795
+ "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00039.safetensors",
796
+ "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00039.safetensors",
797
+ "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00039.safetensors",
798
+ "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00039.safetensors",
799
+ "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00039.safetensors",
800
+ "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00039.safetensors",
801
+ "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00039.safetensors",
802
+ "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00039.safetensors",
803
+ "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00039.safetensors",
804
+ "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00039.safetensors",
805
+ "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00039.safetensors",
806
+ "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00039.safetensors",
807
+ "model.layers.31.block_sparse_moe.gate.weight": "model-00038-of-00039.safetensors",
808
+ "model.layers.31.input_layernorm.weight": "model-00039-of-00039.safetensors",
809
+ "model.layers.31.post_attention_layernorm.weight": "model-00039-of-00039.safetensors",
810
+ "model.layers.31.self_attn.k_proj.weight": "model-00038-of-00039.safetensors",
811
+ "model.layers.31.self_attn.o_proj.weight": "model-00038-of-00039.safetensors",
812
+ "model.layers.31.self_attn.q_proj.weight": "model-00037-of-00039.safetensors",
813
+ "model.layers.31.self_attn.v_proj.weight": "model-00038-of-00039.safetensors",
814
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00039.safetensors",
815
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00039.safetensors",
816
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00039.safetensors",
817
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00039.safetensors",
818
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00039.safetensors",
819
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00039.safetensors",
820
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00039.safetensors",
821
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00039.safetensors",
822
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00039.safetensors",
823
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00039.safetensors",
824
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00039.safetensors",
825
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00039.safetensors",
826
+ "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00039.safetensors",
827
+ "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00039.safetensors",
828
+ "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00039.safetensors",
829
+ "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00039.safetensors",
830
+ "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00039.safetensors",
831
+ "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00039.safetensors",
832
+ "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00039.safetensors",
833
+ "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00039.safetensors",
834
+ "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00039.safetensors",
835
+ "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00039.safetensors",
836
+ "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00039.safetensors",
837
+ "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00039.safetensors",
838
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00039.safetensors",
839
+ "model.layers.4.input_layernorm.weight": "model-00007-of-00039.safetensors",
840
+ "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00039.safetensors",
841
+ "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00039.safetensors",
842
+ "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00039.safetensors",
843
+ "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00039.safetensors",
844
+ "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00039.safetensors",
845
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00039.safetensors",
846
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00039.safetensors",
847
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00039.safetensors",
848
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00039.safetensors",
849
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00039.safetensors",
850
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00039.safetensors",
851
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00039.safetensors",
852
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00039.safetensors",
853
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00039.safetensors",
854
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00039.safetensors",
855
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00039.safetensors",
856
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00039.safetensors",
857
+ "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00039.safetensors",
858
+ "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00039.safetensors",
859
+ "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00039.safetensors",
860
+ "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00039.safetensors",
861
+ "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00039.safetensors",
862
+ "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00039.safetensors",
863
+ "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00039.safetensors",
864
+ "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00039.safetensors",
865
+ "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00039.safetensors",
866
+ "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00039.safetensors",
867
+ "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00039.safetensors",
868
+ "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00039.safetensors",
869
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00039.safetensors",
870
+ "model.layers.5.input_layernorm.weight": "model-00008-of-00039.safetensors",
871
+ "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00039.safetensors",
872
+ "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00039.safetensors",
873
+ "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00039.safetensors",
874
+ "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00039.safetensors",
875
+ "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00039.safetensors",
876
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00039.safetensors",
877
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00039.safetensors",
878
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00039.safetensors",
879
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00039.safetensors",
880
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00039.safetensors",
881
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00039.safetensors",
882
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00039.safetensors",
883
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00039.safetensors",
884
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00039.safetensors",
885
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00039.safetensors",
886
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00039.safetensors",
887
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00039.safetensors",
888
+ "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00039.safetensors",
889
+ "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00039.safetensors",
890
+ "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00039.safetensors",
891
+ "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00039.safetensors",
892
+ "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00039.safetensors",
893
+ "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00039.safetensors",
894
+ "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00039.safetensors",
895
+ "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00039.safetensors",
896
+ "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00039.safetensors",
897
+ "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00039.safetensors",
898
+ "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00039.safetensors",
899
+ "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00039.safetensors",
900
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00039.safetensors",
901
+ "model.layers.6.input_layernorm.weight": "model-00009-of-00039.safetensors",
902
+ "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00039.safetensors",
903
+ "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00039.safetensors",
904
+ "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00039.safetensors",
905
+ "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00039.safetensors",
906
+ "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00039.safetensors",
907
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00039.safetensors",
908
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00039.safetensors",
909
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00039.safetensors",
910
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00039.safetensors",
911
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00039.safetensors",
912
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00039.safetensors",
913
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00039.safetensors",
914
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00039.safetensors",
915
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00039.safetensors",
916
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00039.safetensors",
917
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00039.safetensors",
918
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00039.safetensors",
919
+ "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00039.safetensors",
920
+ "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00039.safetensors",
921
+ "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00039.safetensors",
922
+ "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00039.safetensors",
923
+ "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00039.safetensors",
924
+ "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00039.safetensors",
925
+ "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00039.safetensors",
926
+ "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00039.safetensors",
927
+ "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00039.safetensors",
928
+ "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00039.safetensors",
929
+ "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00039.safetensors",
930
+ "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00039.safetensors",
931
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00009-of-00039.safetensors",
932
+ "model.layers.7.input_layernorm.weight": "model-00010-of-00039.safetensors",
933
+ "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00039.safetensors",
934
+ "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00039.safetensors",
935
+ "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00039.safetensors",
936
+ "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00039.safetensors",
937
+ "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00039.safetensors",
938
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00039.safetensors",
939
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00039.safetensors",
940
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00039.safetensors",
941
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00039.safetensors",
942
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00039.safetensors",
943
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00039.safetensors",
944
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00039.safetensors",
945
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00039.safetensors",
946
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00039.safetensors",
947
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00039.safetensors",
948
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00039.safetensors",
949
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00039.safetensors",
950
+ "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00039.safetensors",
951
+ "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00039.safetensors",
952
+ "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00039.safetensors",
953
+ "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00039.safetensors",
954
+ "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00039.safetensors",
955
+ "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00039.safetensors",
956
+ "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00039.safetensors",
957
+ "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00039.safetensors",
958
+ "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00039.safetensors",
959
+ "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00039.safetensors",
960
+ "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00039.safetensors",
961
+ "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00039.safetensors",
962
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00010-of-00039.safetensors",
963
+ "model.layers.8.input_layernorm.weight": "model-00011-of-00039.safetensors",
964
+ "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00039.safetensors",
965
+ "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00039.safetensors",
966
+ "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00039.safetensors",
967
+ "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00039.safetensors",
968
+ "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00039.safetensors",
969
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00039.safetensors",
970
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00039.safetensors",
971
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00039.safetensors",
972
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00039.safetensors",
973
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00039.safetensors",
974
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00039.safetensors",
975
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00039.safetensors",
976
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00039.safetensors",
977
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00039.safetensors",
978
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00039.safetensors",
979
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00039.safetensors",
980
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00039.safetensors",
981
+ "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00039.safetensors",
982
+ "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00039.safetensors",
983
+ "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00039.safetensors",
984
+ "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00039.safetensors",
985
+ "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00039.safetensors",
986
+ "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00039.safetensors",
987
+ "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00039.safetensors",
988
+ "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00039.safetensors",
989
+ "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00039.safetensors",
990
+ "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00039.safetensors",
991
+ "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00039.safetensors",
992
+ "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00039.safetensors",
993
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00011-of-00039.safetensors",
994
+ "model.layers.9.input_layernorm.weight": "model-00012-of-00039.safetensors",
995
+ "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00039.safetensors",
996
+ "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00039.safetensors",
997
+ "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00039.safetensors",
998
+ "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00039.safetensors",
999
+ "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00039.safetensors",
1000
+ "model.norm.weight": "model-00039-of-00039.safetensors"
1001
+ }
1002
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }