Hugging Face's logo

occiglot
/
occiglot-7b-eu5

Text Generation
Transformers
Safetensors
mistral
text-generation-inference
Inference Endpoints
Model card Files Community
5
malteos commited on
Commit
e2ef0ce
•
1 Parent(s): 5479f93

uploading model files

Browse files
Files changed (15) hide show
  1. README.md +143 -0
  2. config.json +26 -0
  3. generation_config.json +6 -0
  4. lm-datasets-config.yml +398 -0
  5. model-00001-of-00006.safetensors +3 -0
  6. model-00002-of-00006.safetensors +3 -0
  7. model-00003-of-00006.safetensors +3 -0
  8. model-00004-of-00006.safetensors +3 -0
  9. model-00005-of-00006.safetensors +3 -0
  10. model-00006-of-00006.safetensors +3 -0
  11. model.safetensors.index.json +298 -0
  12. special_tokens_map.json +5 -0
  13. tokenizer.json +0 -0
  14. tokenizer.model +3 -0
  15. tokenizer_config.json +42 -0
README.md CHANGED
@@ -1,3 +1,146 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ language:
4
+ - en
5
+ - es
6
+ - de
7
+ - fr
8
+ - it
9
+ pipeline_tag: text-generation
10
  ---
11
+
12
+ ![image/png](https://huggingface.co/datasets/malteos/images/resolve/main/occiglot.medium.png)
13
+
14
+ # Occiglot-7B-EU5
15
+
16
+ > A [polyglot](https://en.wikipedia.org/wiki/Multilingualism#In_individuals) language model for the [Occident](https://en.wikipedia.org/wiki/Occident).
17
+ >
18
+
19
+ **Occiglot-7B-EU5** is a generative language model with 7B parameters supporting the top-5 EU languages (English, Spanish, French, German, and Italian) and trained by the [German Research Center for Artificial Intelligence (DFKI)](https://www.dfki.de/en/web).
20
+ It is based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) and trained on 293B tokens of additional multilingual and code data with a block size of 8,192 tokens per sample.
21
+ Note that the model is a general-purpose base model and was not instruction-fine-tuned nor optimized for chat or other applications.
22
+
23
+ This is the first release of an ongoing open research project for multilingual language models.
24
+ If you want to train a model for your own language or are working on evaluations, please contact us. **We are open for collaborations!**
25
+
26
+
27
+ ### Model details
28
+
29
+ - **Continued-pretraining from:** [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
30
+ - **Model type:** Causal decoder-only transformer language model
31
+ - **Languages:** English, Spanish, French, German, Italian, and code.
32
+ - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html)
33
+ - **Compute resources:** [HessianAI's 42](https://hessian.ai/)
34
+ - **Contributors:** Manuel Brack, Patrick Schramowski, Pedro Ortiz, Malte Ostendorff, Fabio Barth, Georg Rehm, Kristian Kersting
35
+ - **Research labs:** [SAINT](https://www.dfki.de/en/web/research/research-departments/foundations-of-systems-ai) and [SLT](https://www.dfki.de/en/web/research/research-departments/speech-and-language-technology)
36
+
37
+ ### How to use
38
+
39
+ You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
40
+ set a seed for reproducibility:
41
+
42
+ ```python
43
+ >>> from transformers import pipeline, set_seed
44
+ >>> generator = pipeline('text-generation', model='occiglot/occiglot-7b-eu5')
45
+ >>> set_seed(42)
46
+ >>> generator("Hallo, Ich bin ein Sprachmodell,", max_length=40, num_return_sequences=1)
47
+ [{'generated_text': 'Hallo, Ich bin ein Sprachmodell, das dir bei der Übersetzung von Texten zwischen Deutsch und Englisch helfen kann. Wenn du mir einen Text in Deutsch'}]
48
+ ```
49
+
50
+ ## Dataset
51
+
52
+ The training data was split amongst the 4 target languages (de, es, fr, it) and the continuous training in English and code.
53
+
54
+ The data distribution by language (estimated) is as follows:
55
+ - English: ~13%
56
+ - Code: ~5%
57
+ - German: ~20%
58
+ - Spanish: ~20%
59
+ - French: ~20%
60
+ - Italian: ~20%
61
+
62
+ The training data was prepared using [lm-datasets](https://github.com/malteos/lm-datasets).
63
+ The exact data config will be released soon.
64
+
65
+ ## Training settings
66
+
67
+ - Continual pre-training on 128 x A100-80GB on [HessianAI's 42](https://hessian.ai/).
68
+ - Framework: [Determined](https://www.determined.ai/)
69
+ - Precision: bf16
70
+ - Optimizer: AdamW (lr: 0.00001, warmup_steps: 420)
71
+ - Global batch size: 512 (with 8192 blocksize) split over 128 GPUs
72
+ - Cosine Annealing with Warmup
73
+
74
+
75
+ ## Tokenizer
76
+
77
+ Tokenizer is unchanged from [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
78
+
79
+ ## Evaluation
80
+
81
+ Preliminary evaluation results can be found below.
82
+ Please note that the non-English results are based on partially machine-translated datasets and English prompts ([Belebele](https://huggingface.co/datasets/facebook/belebele) and [Okapi framework](https://github.com/nlp-uoregon/Okapi)) and thus should be interpreted with caution, e.g., biased towards English model performance.
83
+ Currently, we are working on more suitable benchmarks for Spanish, French, German, and Italian.
84
+
85
+ ### All languages
86
+
87
+ | **model_name** | **arc_challenge** | **hellaswag** | **belebele** | **mmlu** | **avg** |
88
+ |--------------------------|-------------------|---------------|--------------|----------|---------|
89
+ | Mistral-7B-v0.1 | 0.5277 | 0.6825 | 0.7687 | 0.6287 | 0.6519 |
90
+ | leo-mistral-hessianai-7b | 0.4614 | 0.6423 | 0.6524 | 0.5440 | 0.5750 |
91
+ | Occiglot-7B-EU5 | 0.5083 | 0.7191 | 0.6758 | 0.5432 | 0.6116 |
92
+
93
+ ### English
94
+
95
+ | **model_name** | **arc_challenge** | **hellaswag** | **belebele** | **mmlu** | **avg** |
96
+ |--------------------------|-------------------|---------------|--------------|----------|---------|
97
+ | Mistral-7B-v0.1 | 0.6143 | 0.8344 | 0.8444 | 0.6351 | 0.7321 |
98
+ | leo-mistral-hessianai-7b | 0.5213 | 0.7779 | 0.7356 | 0.5508 | 0.6464 |
99
+ | Occiglot-7B-EU5 | 0.5307 | 0.7900 | 0.7267 | 0.5467 | 0.6485 |
100
+
101
+ ### German
102
+
103
+ | **model_name** | **arc_challenge** | **hellaswag** | **belebele** | **mmlu** | **avg** |
104
+ |--------------------------|-------------------|---------------|--------------|----------|---------|
105
+ | Mistral-7B-v0.1 | 0.4765 | 0.6101 | 0.7411 | 0.5274 | 0.5888 |
106
+ | leo-mistral-hessianai-7b | 0.4739 | 0.6818 | 0.6900 | 0.4887 | 0.5836 |
107
+ | Occiglot-7B-EU5 | 0.4944 | 0.6667 | 0.6467 | 0.4833 | 0.5728 |
108
+
109
+ ### Spanish
110
+
111
+ | **model_name** | **arc_challenge** | **hellaswag** | **belebele** | **mmlu** | **avg** |
112
+ |--------------------------|-------------------|---------------|--------------|----------|---------|
113
+ | Mistral-7B-v0.1 | 0.5256 | 0.6728 | 0.7478 | 0.5432 | 0.6224 |
114
+ | leo-mistral-hessianai-7b | 0.4436 | 0.5970 | 0.6178 | 0.4359 | 0.5236 |
115
+ | Occiglot-7B-EU5 | 0.5085 | 0.7255 | 0.6778 | 0.4997 | 0.6029 |
116
+
117
+ ### French
118
+
119
+ | **model_name** | **arc_challenge** | **hellaswag** | **belebele** | **mmlu** | **avg** |
120
+ |--------------------------|-------------------|---------------|--------------|----------|---------|
121
+ | Mistral-7B-v0.1 | 0.5244 | 0.6651 | 0.7744 | 0.5413 | 0.6263 |
122
+ | leo-mistral-hessianai-7b | 0.4354 | 0.5967 | 0.6222 | 0.4326 | 0.5217 |
123
+ | Occiglot-7B-EU5 | 0.5064 | 0.7125 | 0.6756 | 0.4959 | 0.5976 |
124
+
125
+ ### Italian
126
+
127
+ | **model_name** | **arc_challenge** | **hellaswag** | **belebele** | **mmlu** | **avg** |
128
+ |--------------------------|-------------------|---------------|--------------|----------|---------|
129
+ | Mistral-7B-v0.1 | 0.4979 | 0.6303 | 0.7356 | 0.5372 | 0.6002 |
130
+ | leo-mistral-hessianai-7b | 0.4328 | 0.5580 | 0.5967 | 0.4311 | 0.5047 |
131
+ | Occiglot-7B-EU5 | 0.5013 | 0.7008 | 0.6522 | 0.4949 | 0.5873 |
132
+
133
+
134
+
135
+ ## Acknowledgements
136
+
137
+ The model training was supported by a compute grant at the [42 supercomputer](https://hessian.ai/) which is a central component in the development of [hessian AI](https://hessian.ai/), the [AI Innovation Lab](https://hessian.ai/infrastructure/ai-innovationlab/) ([HMWK](https://wissenschaft.hessen.de) & [HMinD](https://innen.hessen.de)) and the [AI Service Centers](https://hessian.ai/infrastructure/ai-service-centre/) ([BMBF](https://www.bmbf.de/bmbf/en/home/home_node.html)).
138
+ The curation of the training data is partially funded by the [German Federal Ministry for Economic Affairs and Climate Action (BMWK)](https://www.bmwk.de/Navigation/EN/Home/home.html)
139
+ through the project [OpenGPT-X](https://opengpt-x.de/en/) (project no. 68GX21007D).
140
+
141
+
142
+ ## License
143
+
144
+ [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html)
145
+
146
+
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
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": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
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": "4.36.2"
6
+ }
lm-datasets-config.yml ADDED
@@ -0,0 +1,398 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Config file for https://github.com/malteos/lm-datasets
2
+ #
3
+ # EU top-5 (en,fr,es,de,it) + code
4
+ # target size: 300B tokens (train first for 200B tokens)
5
+
6
+ # a fixed random seed for shuffling etc.
7
+ seed: 0
8
+
9
+ # data split settings
10
+ validation_ratio: 0.005 # number of documents in the split: len(dataset) * ratio
11
+ validation_min_total_docs: 1_000 # to be used as validation set, the dataset must have at least n docs
12
+ validation_max_split_docs: 1_000 # number of documents in validation split are capped at this numbers
13
+ validation_min_split_docs: 10 # split must have at least this number of documents, otherwise it will be discarded
14
+ tokenizer_train_ratio: 0.1
15
+
16
+ selected_source_ids:
17
+ - starcoder
18
+
19
+ selected_dataset_ids:
20
+ # english
21
+ - pes2o
22
+ - math_amps
23
+ - eurlex_en
24
+ - wikipedia_20231101_en
25
+ - wikibooks_en
26
+ - wikiquote_en
27
+ - wikinews_en
28
+ - wikisource_en
29
+ - wikivoyage_en
30
+ - colossal_oscar_2015-14_en
31
+ - colossal_oscar_2016-40_en
32
+ - colossal_oscar_2017-43_en
33
+ - colossal_oscar_2018-47_en
34
+ - colossal_oscar_2019-22_en
35
+ - colossal_oscar_2020-24_en
36
+ - colossal_oscar_2020-45_en
37
+ - colossal_oscar_2021-49_en
38
+ - colossal_oscar_2022-27_en
39
+ - colossal_oscar_2022-49_en
40
+ - colossal_oscar_2023-14_en
41
+ - colossal_oscar_2023-23_en
42
+ - pile_of_law_r_legaladvice
43
+ - pile_of_law_atticus_contracts
44
+ - pile_of_law_un_debates
45
+ - proof_pile2_open_web_math
46
+ - parlamint_gb
47
+ - redpajama_stackexchange
48
+
49
+ # french
50
+ - cabernet
51
+ - eurlex_fr
52
+ - legal_mc4_fr
53
+ - wikipedia_20231101_fr
54
+ - wikibooks_fr
55
+ - wikiquote_fr
56
+ - wikinews_fr
57
+ - wikisource_fr
58
+ - wikivoyage_fr
59
+ - colossal_oscar_2015-14_fr
60
+ - colossal_oscar_2016-40_fr
61
+ - colossal_oscar_2017-43_fr
62
+ - colossal_oscar_2018-47_fr
63
+ - colossal_oscar_2019-22_fr
64
+ - colossal_oscar_2020-24_fr
65
+ - colossal_oscar_2020-45_fr
66
+ - colossal_oscar_2021-49_fr
67
+ - colossal_oscar_2022-27_fr
68
+ - colossal_oscar_2022-49_fr
69
+ - colossal_oscar_2023-14_fr
70
+ - colossal_oscar_2023-23_fr
71
+ - opensubtitles_fr
72
+ - parlamint_fr
73
+
74
+ # spanish
75
+ - spanish_legal
76
+ - eurlex_es
77
+ - legal_mc4_es
78
+ - wikipedia_20231101_es
79
+ - wikibooks_es
80
+ - wikiquote_es
81
+ - wikinews_es
82
+ - wikisource_es
83
+ - wikivoyage_es
84
+ - colossal_oscar_2015-14_es
85
+ - colossal_oscar_2016-40_es
86
+ - colossal_oscar_2017-43_es
87
+ - colossal_oscar_2018-47_es
88
+ - colossal_oscar_2019-22_es
89
+ - colossal_oscar_2020-24_es
90
+ - colossal_oscar_2020-45_es
91
+ - colossal_oscar_2021-49_es
92
+ - colossal_oscar_2022-27_es
93
+ - colossal_oscar_2022-49_es
94
+ - colossal_oscar_2023-14_es
95
+ - colossal_oscar_2023-23_es
96
+ - opensubtitles_es
97
+ - parlamint_es
98
+
99
+ # german
100
+ - openlegaldata
101
+ - dewac
102
+ - eurlex_de
103
+ - legal_mc4_de
104
+ - wikipedia_20231101_de
105
+ - wikibooks_de
106
+ - wikiquote_de
107
+ - wikinews_de
108
+ - wikisource_de
109
+ - wikivoyage_de
110
+ - colossal_oscar_2015-14_de
111
+ - colossal_oscar_2016-40_de
112
+ - colossal_oscar_2017-43_de
113
+ - colossal_oscar_2018-47_de
114
+ - colossal_oscar_2019-22_de
115
+ - colossal_oscar_2020-24_de
116
+ - colossal_oscar_2020-45_de
117
+ - colossal_oscar_2021-49_de
118
+ - colossal_oscar_2022-27_de
119
+ - colossal_oscar_2022-49_de
120
+ - colossal_oscar_2023-14_de
121
+ - colossal_oscar_2023-23_de
122
+ - open_discourse_bundestag
123
+ - tagesschau_2018_2023
124
+ - opensubtitles_de
125
+ - parlamint_at
126
+
127
+ # italian
128
+ - itwac
129
+ - eurlex_it
130
+ - legal_mc4_it
131
+ - wikipedia_20231101_it
132
+ - wikibooks_it
133
+ - wikiquote_it
134
+ - wikinews_it
135
+ - wikisource_it
136
+ - wikivoyage_it
137
+ - colossal_oscar_2015-14_it
138
+ - colossal_oscar_2016-40_it
139
+ - colossal_oscar_2017-43_it
140
+ - colossal_oscar_2018-47_it
141
+ - colossal_oscar_2019-22_it
142
+ - colossal_oscar_2020-24_it
143
+ - colossal_oscar_2020-45_it
144
+ - colossal_oscar_2021-49_it
145
+ - colossal_oscar_2022-27_it
146
+ - colossal_oscar_2022-49_it
147
+ - colossal_oscar_2023-14_it
148
+ - colossal_oscar_2023-23_it
149
+ - opensubtitles_it
150
+ - parlamint_it
151
+ - tatoeba_translation_en_fr
152
+ - tatoeba_translation_en_es
153
+ - tatoeba_translation_en_it
154
+ - tatoeba_translation_fr_it
155
+ - tatoeba_translation_es_fr
156
+ - tatoeba_translation_es_it
157
+ - tatoeba_translation_de_en
158
+ - tatoeba_translation_de_fr
159
+ - tatoeba_translation_de_es
160
+ - tatoeba_translation_de_it
161
+ - opus100_translation_de_en
162
+ - opus100_translation_en_es
163
+ - opus100_translation_en_fr
164
+ - opus100_translation_en_it
165
+ - wmt19_translation_de_en
166
+ - wmt19_translation_fr_de
167
+
168
+ sampling_factor_by_dataset_id:
169
+ redpajama_stackexchange: 0.1
170
+ pes2o: 0.1
171
+ math_amps: 0.1
172
+ openlegaldata: 0.75
173
+ dewac: 0.05
174
+ itwac: 1
175
+ cabernet: 1
176
+ spanish_legal: 0.1
177
+ eurlex_de: 0.5
178
+ eurlex_en: 0.5
179
+ eurlex_es: 1
180
+ eurlex_fr: 1
181
+ eurlex_it: 1
182
+ legal_mc4_de: 0.1
183
+ legal_mc4_es: 0.25
184
+ legal_mc4_fr: 0.25
185
+ legal_mc4_it: 1
186
+ wikipedia_20231101_de: 2
187
+ wikibooks_de: 1
188
+ wikiquote_de: 1
189
+ wikinews_de: 2
190
+ wikisource_de: 1
191
+ wikivoyage_de: 1
192
+ wikipedia_20231101_en: 1
193
+ wikibooks_en: 1
194
+ wikiquote_en: 0.25
195
+ wikinews_en: 1
196
+ wikisource_en: 1
197
+ wikivoyage_en: 1
198
+ wikipedia_20231101_es: 2
199
+ wikibooks_es: 1
200
+ wikiquote_es: 1
201
+ wikinews_es: 2
202
+ wikisource_es: 1
203
+ wikivoyage_es: 1
204
+ wikipedia_20231101_fr: 2
205
+ wikibooks_fr: 1
206
+ wikiquote_fr: 1
207
+ wikinews_fr: 2
208
+ wikisource_fr: 1
209
+ wikivoyage_fr: 1
210
+ wikipedia_20231101_it: 2
211
+ wikibooks_it: 1
212
+ wikiquote_it: 1
213
+ wikinews_it: 2
214
+ wikisource_it: 1
215
+ wikivoyage_it: 1
216
+ colossal_oscar_2015-14_de: 1
217
+ colossal_oscar_2016-40_de: 0.95
218
+ colossal_oscar_2017-43_de: 0.1
219
+ colossal_oscar_2018-47_de: 0.1
220
+ colossal_oscar_2019-22_de: 0.1
221
+ colossal_oscar_2020-24_de: 0.1
222
+ colossal_oscar_2020-45_de: 0.1
223
+ colossal_oscar_2021-49_de: 0.1
224
+ colossal_oscar_2022-27_de: 0.1
225
+ colossal_oscar_2022-49_de: 0.1
226
+ colossal_oscar_2023-14_de: 0.95
227
+ colossal_oscar_2023-23_de: 1
228
+ colossal_oscar_2015-14_en: 0.05
229
+ colossal_oscar_2016-40_en: 0.05
230
+ colossal_oscar_2017-43_en: 0.001
231
+ colossal_oscar_2018-47_en: 0.001
232
+ colossal_oscar_2019-22_en: 0.001
233
+ colossal_oscar_2020-24_en: 0.001
234
+ colossal_oscar_2020-45_en: 0.001
235
+ colossal_oscar_2021-49_en: 0.001
236
+ colossal_oscar_2022-27_en: 0.001
237
+ colossal_oscar_2022-49_en: 0.001
238
+ colossal_oscar_2023-14_en: 0.05
239
+ colossal_oscar_2023-23_en: 0.05
240
+ colossal_oscar_2015-14_es: 1
241
+ colossal_oscar_2016-40_es: 1
242
+ colossal_oscar_2017-43_es: 0.25
243
+ colossal_oscar_2018-47_es: 0.1
244
+ colossal_oscar_2019-22_es: 0.1
245
+ colossal_oscar_2020-24_es: 0.1
246
+ colossal_oscar_2020-45_es: 0.1
247
+ colossal_oscar_2021-49_es: 0.1
248
+ colossal_oscar_2022-27_es: 0.1
249
+ colossal_oscar_2022-49_es: 0.3
250
+ colossal_oscar_2023-14_es: 1
251
+ colossal_oscar_2023-23_es: 1
252
+ colossal_oscar_2015-14_fr: 1
253
+ colossal_oscar_2016-40_fr: 1
254
+ colossal_oscar_2017-43_fr: 0.25
255
+ colossal_oscar_2018-47_fr: 0.25
256
+ colossal_oscar_2019-22_fr: 0.1
257
+ colossal_oscar_2020-24_fr: 0.1
258
+ colossal_oscar_2020-45_fr: 0.1
259
+ colossal_oscar_2021-49_fr: 0.1
260
+ colossal_oscar_2022-27_fr: 0.1
261
+ colossal_oscar_2022-49_fr: 0.75
262
+ colossal_oscar_2023-14_fr: 1
263
+ colossal_oscar_2023-23_fr: 1
264
+ starcoder_emacs-lisp: 0.1
265
+ starcoder_literate-haskell: 0.1
266
+ starcoder_shell: 0.1
267
+ starcoder_ada: 0.1
268
+ starcoder_erlang: 0.1
269
+ starcoder_lua: 0.1
270
+ starcoder_smalltalk: 0.1
271
+ starcoder_agda: 0.1
272
+ starcoder_f-sharp: 0.1
273
+ starcoder_makefile: 0.1
274
+ starcoder_solidity: 0.1
275
+ starcoder_alloy: 0.1
276
+ starcoder_fortran: 0.1
277
+ starcoder_maple: 0.1
278
+ starcoder_sparql: 0.1
279
+ starcoder_antlr: 0.1
280
+ starcoder_git-commits-cleaned: 0.05
281
+ starcoder_markdown: 0.05
282
+ starcoder_sql: 0.1
283
+ starcoder_applescript: 0.1
284
+ starcoder_github-issues-filtered-structured: 0.075
285
+ starcoder_mathematica: 0.1
286
+ starcoder_stan: 0.1
287
+ starcoder_assembly: 0.1
288
+ starcoder_glsl: 0.1
289
+ starcoder_matlab: 0.1
290
+ starcoder_standard-ml: 0.1
291
+ starcoder_augeas: 0.1
292
+ starcoder_go: 0.05
293
+ starcoder_ocaml: 0.1
294
+ starcoder_stata: 0.1
295
+ starcoder_awk: 0.1
296
+ starcoder_groovy: 0.1
297
+ starcoder_pascal: 0.1
298
+ starcoder_systemverilog: 0.1
299
+ starcoder_batchfile: 0.1
300
+ starcoder_haskell: 0.1
301
+ starcoder_perl: 0.1
302
+ starcoder_tcl: 0.1
303
+ starcoder_bluespec: 0.1
304
+ starcoder_html: 0.05
305
+ starcoder_php: 0.05
306
+ starcoder_tcsh: 0.1
307
+ starcoder_c: 0.05
308
+ starcoder_idris: 0.1
309
+ starcoder_powershell: 0.1
310
+ starcoder_tex: 0.1
311
+ starcoder_c-sharp: 0.05
312
+ starcoder_isabelle: 0.1
313
+ starcoder_prolog: 0.1
314
+ starcoder_thrift: 0.1
315
+ starcoder_clojure: 0.1
316
+ starcoder_java: 0.05
317
+ starcoder_protocol-buffer: 0.1
318
+ starcoder_typescript: 0.05
319
+ starcoder_cmake: 0.1
320
+ starcoder_java-server-pages: 0.1
321
+ starcoder_python: 0.05
322
+ starcoder_verilog: 0.1
323
+ starcoder_coffeescript: 0.1
324
+ starcoder_javascript: 0.05
325
+ starcoder_r: 0.1
326
+ starcoder_vhdl: 0.1
327
+ starcoder_common-lisp: 0.1
328
+ starcoder_json: 0.1
329
+ starcoder_racket: 0.1
330
+ starcoder_visual-basic: 0.1
331
+ starcoder_cpp: 0.05
332
+ starcoder_julia: 0.1
333
+ starcoder_restructuredtext: 0.1
334
+ starcoder_xslt: 0.1
335
+ starcoder_css: 0.1
336
+ starcoder_jupyter-scripts-dedup-filtered: 0.1
337
+ starcoder_rmarkdown: 0.1
338
+ starcoder_yacc: 0.1
339
+ starcoder_cuda: 0.1
340
+ starcoder_jupyter-structured-clean-dedup: 0.1
341
+ starcoder_ruby: 0.1
342
+ starcoder_yaml: 0.1
343
+ starcoder_dart: 0.1
344
+ starcoder_kotlin: 0.1
345
+ starcoder_rust: 0.1
346
+ starcoder_zig: 0.1
347
+ starcoder_dockerfile: 0.1
348
+ starcoder_lean: 0.1
349
+ starcoder_sas: 0.1
350
+ starcoder_elixir: 0.1
351
+ starcoder_literate-agda: 0.1
352
+ starcoder_scala: 0.1
353
+ starcoder_elm: 0.1
354
+ starcoder_literate-coffeescript: 0.1
355
+ starcoder_scheme: 0.1
356
+ pile_of_law_r_legaladvice: 1
357
+ pile_of_law_atticus_contracts: 0.25
358
+ pile_of_law_un_debates: 1
359
+ open_discourse_bundestag: 0.5
360
+ tagesschau_2018_2023: 1
361
+ proof_pile2_open_web_math: 0.25
362
+ tatoeba_translation_en_fr: 1
363
+ tatoeba_translation_en_es: 1
364
+ tatoeba_translation_en_it: 1
365
+ tatoeba_translation_fr_it: 1
366
+ tatoeba_translation_es_fr: 1
367
+ tatoeba_translation_es_it: 1
368
+ tatoeba_translation_de_en: 1
369
+ tatoeba_translation_de_fr: 1
370
+ tatoeba_translation_de_es: 1
371
+ tatoeba_translation_de_it: 1
372
+ opus100_translation_de_en: 1
373
+ opus100_translation_en_es: 1
374
+ opus100_translation_en_fr: 1
375
+ opus100_translation_en_it: 1
376
+ wmt19_translation_de_en: 1
377
+ wmt19_translation_fr_de: 1
378
+ opensubtitles_es: 1
379
+ opensubtitles_fr: 1
380
+ opensubtitles_de: 1
381
+ opensubtitles_it: 1
382
+ parlamint_es: 1
383
+ parlamint_it: 1
384
+ parlamint_at: 1
385
+ parlamint_fr: 1
386
+ parlamint_gb: 1
387
+ colossal_oscar_2015-14_it: 1
388
+ colossal_oscar_2016-40_it: 1
389
+ colossal_oscar_2017-43_it: 0.75
390
+ colossal_oscar_2018-47_it: 0.75
391
+ colossal_oscar_2019-22_it: 0.75
392
+ colossal_oscar_2020-24_it: 0.75
393
+ colossal_oscar_2020-45_it: 0.75
394
+ colossal_oscar_2021-49_it: 0.75
395
+ colossal_oscar_2022-27_it: 0.75
396
+ colossal_oscar_2022-49_it: 0.75
397
+ colossal_oscar_2023-14_it: 0.9
398
+ colossal_oscar_2023-23_it: 1
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3572c45423614e2b874ae7d421fd4f850e7cabc7e966980547b2cdce71e515f0
3
+ size 4987196936
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb2cd75b9f7dbb8ba0256ba6771bc7fbc54310ea9bb3f57d57eed297ea2d3f4
3
+ size 4899116440
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c560c912b037e5af4c78bab14eacc2c3fc5f7724371fe68e6f0b0fe4ffafc19
3
+ size 4999813120
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729463205aaed76447ca86177110de7a825fe8e6d8b7db5dfd35caef42cd2531
3
+ size 4999813128
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897a386e7f7a04a78c0c130538f715c7d4c699ba471919b2dc3d381a67f358bb
3
+ size 4832007496
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f37c13b68f2eda900c982f0dd6cae586d3df65dfa7bcf87dbb6717a8e434f6
3
+ size 4249014896
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28966928384
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
296
+ "model.norm.weight": "model-00006-of-00006.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }