Hugging Face's logo

sandbox-ai
/
Llama-3.1-Tango-8b-int4

Text Generation
Transformers
Safetensors
English
Spanish
llama
text-generation-inference
unsloth
trl
sft
tango
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
tatakof commited on
Commit
bb87e93
·
verified ·
1 Parent(s): 8c60d02

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +141 -2
README.md CHANGED
@@ -7,9 +7,16 @@ tags:
7
  - llama
8
  - trl
9
  - sft
10
- license: apache-2.0
 
11
  language:
12
  - en
 
 
 
 
 
 
13
  ---
14
 
15
  # Uploaded model
@@ -18,6 +25,138 @@ language:
18
  - **License:** apache-2.0
19
  - **Finetuned from model :** unsloth/meta-llama-3.1-8b-bnb-4bit
20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
22
 
23
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
7
  - llama
8
  - trl
9
  - sft
10
+ - tango
11
+ license: llama3.1
12
  language:
13
  - en
14
+ - es
15
+ datasets:
16
+ - spanish-ir/messirve
17
+ - tatakof/messi_mod-v0.0.2
18
+ pipeline_tag: text-generation
19
+ library_name: transformers
20
  ---
21
 
22
  # Uploaded model
 
25
  - **License:** apache-2.0
26
  - **Finetuned from model :** unsloth/meta-llama-3.1-8b-bnb-4bit
27
 
28
+
29
+ ## Evaluation Metrics
30
+ |Task |Name |Description |Language|Metric |Task type |
31
+ |--------------------------------------------------------------------------------------------------------|-------------------|-----------------------------------------------------------------------|--------|--------------|------------------------------------------|
32
+ |[AQuAS](https://huggingface.co/datasets/IIC/AQuAS) |AQuAS |Abstractive Question-Answering in Spanish |ES |sas_encoder |Abstractive QA |
33
+ |[ARC_ca](https://huggingface.co/datasets/projecte-aina/arc_ca) |ARC_ca |Grade-school level science questions in Catalan |CA |acc |Multi choice QA |
34
+ |[BEC2016eu](https://huggingface.co/datasets/orai-nlp/basqueGLUE) |BEC2016eu |Basque Election Campaign 2016 Opinion Dataset |EU |f1 |Sentiment Analysis |
35
+ |[Belebele Glg](https://huggingface.co/datasets/facebook/belebele) |Belebele Glg |Reading Comprehension in Galician |GL |acc |Reading Comprehension |
36
+ |[BertaQA](https://huggingface.co/datasets/HiTZ/BertaQA) |BertaQA |Trivia dataset with global and local questions about the Basque Country|EU |acc |Multi choice QA |
37
+ |[BHTCv2](https://huggingface.co/datasets/orai-nlp/basqueGLUE) |BHTCv2 |Topic Classification of News Headlines in Basque |EU |f1 |Classification, Topic Classification |
38
+ |[caBREU](https://huggingface.co/datasets/projecte-aina/caBreu) |caBREU |Article Summarization in Catalan |CA |bleu |Summarization |
39
+ |[CatalanQA](https://huggingface.co/datasets/projecte-aina/catalanqa) |CatalanQA |Extractive QA in Catalan |CA |f1 |Extractive QA |
40
+ |[CatCoLA](https://huggingface.co/datasets/nbel/CatCoLA) |CatCoLA |Linguistic Acceptability in Catalan |CA |mcc |Linguistic Acceptability |
41
+ |[ClinDiagnosES](https://huggingface.co/datasets/LenguajeNaturalAI/ClinDiagnosES) |ClinDiagnosES |Diagnosis of clinical cases in Spanish |ES |sas_encoder |Open QA |
42
+ |[ClinTreatES](https://huggingface.co/datasets/LenguajeNaturalAI/ClinTreatES) |ClinTreatES |Treatment for clinical cases in Spanish |ES |sas_encoder |Open QA |
43
+ |[COPA_ca](https://huggingface.co/datasets/projecte-aina/COPA-ca) |COPA_ca |Choice Of Plausible Alternatives in Catalan |CA |acc |Reasoning |
44
+ |[CoQCat](https://huggingface.co/datasets/projecte-aina/CoQCat) |CoQCat |Conversational Question Answering in Catalan |CA |f1 |Extractive QA |
45
+ |[Crows Pairs Spanish](https://huggingface.co/datasets/multilingual-crows-pairs/multilingual-crows-pairs)|Crows Pairs Spanish|Bias evaluation using stereotypes |ES |pct_stereotype|Bias Detection |
46
+ |[EpecKorrefBin](https://huggingface.co/datasets/orai-nlp/basqueGLUE) |EpecKorrefBin |Coreference resolution in Basque |EU |acc |Coreference Resolution, Textual Entailment|
47
+ |[EsCoLA](https://huggingface.co/datasets/nbel/EsCoLA) |EsCoLA |Spanish Corpus of Linguistic Acceptability |ES |mcc |Linguistic Acceptability |
48
+ |[EusExams](https://huggingface.co/datasets/HiTZ/EusExams) |EusExams |Public Service examinations questions in Basque |EU |acc |Multi choice QA |
49
+ |[EusProficiency](https://huggingface.co/datasets/HiTZ/EusProficiency) |EusProficiency |C1-level proficiency questions in Basque |EU |acc |Multi choice QA |
50
+ |[EusReading](https://huggingface.co/datasets/HiTZ/EusReading) |EusReading |EGA exams reading comprehension in Basque |EU |acc |Multi choice QA |
51
+ |[EusTrivia](https://huggingface.co/datasets/HiTZ/EusTrivia) |EusTrivia |Trivia questions in Basque |EU |acc |Multi choice QA |
52
+ |[Fake News ES](https://huggingface.co/datasets/mariagrandury/fake_news_corpus_spanish) |Fake News ES |Fake News Detection in Spanish |ES |acc |Classification |
53
+ |[GalCoLA](https://huggingface.co/datasets/proxectonos/galcola) |GalCoLA |Galician Corpus of Linguistic Acceptability |GL |mcc |Linguistic Acceptability |
54
+ |[HumorQA](https://huggingface.co/datasets/LenguajeNaturalAI/HumorQA) |HumorQA |White humour joke classification |ES |acc |Classification |
55
+ |[MGSM_ca](https://huggingface.co/datasets/projecte-aina/mgsm_ca) |MGSM_ca |Grade-school math problems in Catalan |CA |exact_match |Math Reasoning |
56
+ |[MGSM_es](https://huggingface.co/datasets/juletxara/mgsm) |MGSM_es |Grade-school math problems in Spanish |ES |exact_match |Math Reasoning |
57
+ |[MGSM_eu](https://huggingface.co/datasets/HiTZ/MGSM-eu) |MGSM_eu |Grade-school math problems in Basque |EU |exact_match |Math Reasoning |
58
+ |[MGSM_gl](https://huggingface.co/datasets/proxectonos/mgsm_gl) |MGSM_gl |Grade-school math problems in Galician |GL |exact_match |Math Reasoning |
59
+ |[NoticIA](https://huggingface.co/datasets/Iker/NoticIA) |NoticIA |A Clickbait Article Summarization Dataset in Spanish |ES |rouge1 |Summarization |
60
+ |[OffendES](https://huggingface.co/datasets/SINAI/OffendES) |OffendES |Clasificación de comentarios ofensivos en español |ES |acc |Classification |
61
+ |[OpenBookQA_ca](https://huggingface.co/datasets/projecte-aina/openbookqa_ca) |OpenBookQA_ca |Multi-step reasoning QA in Catalan |CA |acc |Reasoning |
62
+ |[OpenBookQA_gl](https://huggingface.co/datasets/proxectonos/openbookqa_gl) |OpenBookQA_gl |Multi-step reasoning QA in Galician |GL |acc |Reasoning |
63
+ |[Parafraseja](https://huggingface.co/datasets/projecte-aina/Parafraseja) |Parafraseja |Paraphrase identification in Catalan |CA |acc |Paraphrasing |
64
+ |[ParafrasesGL](https://huggingface.co/datasets/proxectonos/parafrases_gl) |ParafrasesGL |Paraphrase identification in Galician |GL |acc |Paraphrasing |
65
+ |[PAWS_ca](https://huggingface.co/datasets/projecte-aina/PAWS-ca) |PAWS_ca |Paraphrase Adversaries from Word Scrambling in Catalan |CA |acc |Paraphrasing |
66
+ |[PAWS-X_es](https://huggingface.co/datasets/google-research-datasets/paws-x) |PAWS-X_es |Paraphrase Adversaries from Word Scrambling in Spanish |ES |acc |Paraphrasing |
67
+ |[PAWS_gl](https://huggingface.co/datasets/proxectonos/PAWS-gl) |PAWS_gl |Paraphrase Adversaries from Word Scrambling in Galician |GL |acc |Paraphrasing |
68
+ |[PIQA_ca](https://huggingface.co/datasets/projecte-aina/piqa_ca) |PIQA_ca |Physical Interaction QA in Catalan |CA |acc |Reasoning |
69
+ |[QNLIeu](https://huggingface.co/datasets/orai-nlp/basqueGLUE) |QNLIeu |Textual Entailment in Basque |EU |acc |NLI, Textual Entailment |
70
+ |[RagQuAS](https://huggingface.co/datasets/IIC/RagQuAS) |RagQuAS |Retrieval-Augmented-Generation and Question-Answering in Spanish |ES |sas_encoder |Abstractive QA |
71
+ |[SIQA_ca](https://huggingface.co/datasets/projecte-aina/siqa_ca) |SIQA_ca |Social Interaction QA in Catalan |CA |acc |Reasoning |
72
+ |[SpaLawEx](https://huggingface.co/datasets/LenguajeNaturalAI/examenes_abogacia) |SpaLawEx |Spanish Law School Access Exams |ES |acc |Multi choice QA |
73
+ |[SummarizationGL](https://huggingface.co/datasets/proxectonos/summarization_gl) |SummarizationGL |Abstractive Summarization in Galician |GL |bleu |Summarization |
74
+ |[TE-ca](https://huggingface.co/datasets/projecte-aina/teca) |TE-ca |Textual Entailment in Catalan |CA |acc |Textual Entailment |
75
+ |[TELEIA](https://huggingface.co/datasets/gonzmart/teleia) |TELEIA |Test de Español como Lengua Extranjera para Inteligencia Artificial |ES |acc |Multi choice QA |
76
+ |[VaxxStance](https://huggingface.co/datasets/orai-nlp/basqueGLUE) |VaxxStance |Stance detection on the Antivaxxers movement |EU |f1 |Sentiment Analysis, Stance Detection |
77
+ |[WiCeu](https://huggingface.co/datasets/orai-nlp/basqueGLUE) |WiCeu |Word sense disambiguation in Basque |EU |acc |Textual Entailment |
78
+ |[WNLI_ca](https://huggingface.co/datasets/projecte-aina/wnli-ca) |WNLI_ca |Winograd-schema-type dataset in Catalan |CA |acc |NLI, Textual Entailment |
79
+ |[WNLI ES](huggingface.co/datasets/PlanTL-GOB-ES/wnli-es) |WNLI ES |Winograd-schema-type dataset in Spanish |ES |acc |NLI, Textual Entailment |
80
+ |[XCOPA_eu](https://huggingface.co/datasets/HiTZ/XCOPA-eu) |XCOPA_eu |Choice Of Plausible Alternatives in Basque |EU |acc |Reasoning |
81
+ |[XNLI_ca](https://huggingface.co/datasets/projecte-aina/xnli-ca) |XNLI_ca |Cross-lingual Natural Language Inference in Catalan |CA |acc |NLI, Textual Entailment |
82
+ |[XNLI_es](https://huggingface.co/datasets/facebook/xnli) |XNLI_es |Cross-lingual Natural Language Inference in Spanish |ES |acc |NLI |
83
+ |[XNLI_eu](https://huggingface.co/datasets/HiTZ/xnli-eu) |XNLI_eu |Cross-lingual Natural Language Inference in Basque |EU |acc |NLI, Textual Entailment |
84
+ |[XQuAD_ca](https://huggingface.co/datasets/projecte-aina/xquad-ca) |XQuAD_ca |Cross-lingual Question Answering Dataset in Catalan |CA |f1 |Extractive QA |
85
+ |[XQuAD_es](https://huggingface.co/datasets/google/xquad) |XQuAD_es |Cross-lingual Question Answering Dataset in Spanish |ES |f1 |Extractive QA |
86
+ |[xStoryCloze_ca](https://huggingface.co/datasets/projecte-aina/xstorycloze_ca) |xStoryCloze_ca |Narrative completion in Catalan |CA |acc |Reasoning |
87
+ |[xStoryCloze_es](https://huggingface.co/datasets/juletxara/xstory_cloze) |xStoryCloze_es |Narrative completion in Spanish |ES |acc |Reasoning |
88
+ |[xStoryCloze_eu](https://huggingface.co/datasets/juletxara/xstory_cloze) |xStoryCloze_eu |Narrative completion in Basque |EU |acc |Reasoning |
89
+
90
+
91
+ ## Usage:
92
+
93
+ You can use the model using HuggingFace Transformers library with 2 or more 80GB GPUs (NVIDIA Ampere or newer) with at least 150GB of free disk space to accomodate the download.
94
+
95
+ This code has been tested on Transformers v4.44.0, torch v2.4.0 and 2 A100 80GB GPUs, but any setup that supports ```meta-llama/Llama-3.1-70B-Instruct``` should support this model as well. If you run into problems, you can consider doing ```pip install -U transformers```.
96
+ ```python
97
+ # Use a pipeline as a high-level helper
98
+ from transformers import pipeline
99
+
100
+ pipe = pipeline("text-generation", model="sandbox-ai/Llama-3.1-Tango-8b-f16")
101
+ ```
102
+
103
+
104
+ ## References(s):
105
+
106
+ * TODO
107
+
108
+ ## Model Architecture:
109
+ **Architecture Type:** Transformer <br>
110
+ **Network Architecture:** Llama 3.1 <br>
111
+
112
+ ## Input:
113
+ **Input Type(s):** Text <br>
114
+ **Input Format:** String <br>
115
+ **Input Parameters:** One Dimensional (1D) <br>
116
+ **Other Properties Related to Input:** Max of 128k tokens<br>
117
+
118
+ ## Output:
119
+ **Output Type(s):** Text <br>
120
+ **Output Format:** String <br>
121
+ **Output Parameters:** One Dimensional (1D) <br>
122
+ **Other Properties Related to Output:** Max of 4k tokens <br>
123
+
124
+
125
+
126
+ # Training & Evaluation:
127
+ - TODO
128
+
129
+ # Dataset:
130
+
131
+ **MessIRve: A Large-Scale Spanish Information Retrieval Dataset** <br>
132
+ * [spanish/-ir/messirve](https://huggingface.co/datasets/spanish-ir/messirve) <br>
133
+ ** messi_mod-v0.0.2
134
+ [tatakof/messi_mod-v0.0.2](https://huggingface.co/datasets/tatakof/messi_mod-v0.0.2)
135
+
136
+ ## Citation
137
+
138
+ ```bibtex
139
+ @article{valentini2024messirve,
140
+ title={MessIRve: A Large-Scale Spanish Information Retrieval Dataset},
141
+ author={Francisco Valentini and Viviana Cotik and Damián Furman and Ivan Bercovich and Edgar Altszyler and Juan Manuel Pérez},
142
+ year={2024},
143
+ eprint={2409.05994},
144
+ journal={arxiv:2409.05994},
145
+ archivePrefix={arXiv},
146
+ primaryClass={cs.CL},
147
+ url={https://arxiv.org/abs/2409.05994},
148
+ }
149
+
150
+ @misc{wang2024helpsteer2preferencecomplementingratingspreferences,
151
+ title={HelpSteer2-Preference: Complementing Ratings with Preferences},
152
+ author={Zhilin Wang and Alexander Bukharin and Olivier Delalleau and Daniel Egert and Gerald Shen and Jiaqi Zeng and Oleksii Kuchaiev and Yi Dong},
153
+ year={2024},
154
+ eprint={2410.01257},
155
+ archivePrefix={arXiv},
156
+ primaryClass={cs.LG},
157
+ url={https://arxiv.org/abs/2410.01257},
158
+ }
159
+
160
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
161
 
162
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)