Pythainlp
Rank:Average Model Cost: $0.0000
Number of Runs: 3,997
Models by this creator
thainer-corpus-v2-base-model
thainer-corpus-v2-base-model
This is a Named Entity Recognition model that trained with Thai NER v2.0 Corpus Training script and split data: https://zenodo.org/record/7761354 The model was trained by WangchanBERTa base model. Validation from the Validation set Precision: 0.830336794125095 Recall: 0.873701039168665 F1: 0.8514671513892494 Accuracy: 0.9736483416628805 Test from the Test set Precision: 0.8199168093956447 Recall: 0.8781446540880503 F1: 0.8480323927622422 Accuracy: 0.9724346779516247 Download: HuggingFace Hub Read more: Thai NER v2.0 Inference Huggingface doesn't support inference token classification for Thai and It will give wrong tag. You must using this code. output: Cite or BibTeX
$-/run
2.9K
Huggingface
wangchanglm-7.5B-sft-enth
$-/run
324
Huggingface
wangchanglm-7.5B-sft-en
$-/run
245
Huggingface
wangchanglm-7.5B-sft-enth-sharded
wangchanglm-7.5B-sft-enth-sharded
Model Card for WangChanGLM 🐘 - The Multilingual Instruction-Following Model WangChanGLM is a multilingual, instruction-finetuned Facebook XGLM-7.5B using open-source, commercially permissible datasets (LAION OIG chip2 and infill_dbpedia, DataBricks Dolly v2, OpenAI TL;DR, and Hello-SimpleAI HC3; about 400k examples), released under CC-BY SA 4.0. The models are trained to perform a subset of instruction-following tasks we found most relevant namely: reading comprehension, brainstorming, and creative writing. We provide the weights for a model finetuned on an English-only dataset (wangchanglm-7.5B-sft-en) and another checkpoint further finetuned on Google-Translated Thai dataset (wangchanglm-7.5B-sft-enth). We perform Vicuna-style evaluation using both humans and ChatGPT (in our case, gpt-3.5-turbo since we are still on the waitlist for gpt-4) and observe some discrepancies between the two types of annoators. All training and evaluation codes are shared under the Apache-2.0 license in our Github, as well as datasets and model weights on HuggingFace. In a similar manner to Dolly v2, we use only use open-source, commercially permissive pretrained models and datasets, our models are neither restricted by non-commercial clause like models that use LLaMA as base nor non-compete clause like models that use self-instruct datasets from ChatGPT. See our live demo here. Developed by: PyThaiNLP and VISTEC-depa AI Research Institute of Thailand Model type: Finetuned XGLM-7.5B Language(s) (NLP): en, th, ja, vi capacibilities evaluated, theoretically all 30 languages of XGLM-7.5B License: CC-BY SA 4.0 Model Sources Repository: pythainlp/wangchanglm Blog: Medium Demo: Colab notebook Uses Direct Use Intended to be use as an instruction-following model for reading comprehension, brainstorming and creative writing. Downstream Use The model can be finetuned for any typical instruction-following use cases. Out-of-Scope Use We do not expect the models to perform well in math problems, reasoning, and factfulness. We intentionally filter out training examples from these use cases. Bias, Risks, and Limitations We noticed similar limitations to other finetuned instruction followers such as math problems, reasoning, and factfulness. Even though the models do not perform on the level that we expect them to be abused, they do contain undesirable biases and toxicity and should be further optimized for your particular use cases. Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. How to Get Started with the Model Use the code below to get started with the model. Training Details Training Data Finetuning datasets are sourced from LAION OIG chip2 and infill_dbpedia (Apache-2.0), DataBricks Dolly v2 (Apache-2.0), OpenAI TL;DR (MIT), and Hello-SimpleAI HC3 (CC-BY SA). Training Procedure See pythainlp/wangchanglm. Training regime: LoRA with 4 GPUs. See more details at pythainlp/wangchanglm. Evaluation We performed automatic evaluation in the style of Vicuna and human evaluation. See more details from our blog. Environmental Impact Experiments were conducted using a private infrastructure, which has a carbon efficiency of 0.432 kgCO2eq/kWh. A cumulative of 500 hours of computation was performed on hardware of type Tesla V100-SXM2-32GB (TDP of 300W). Total emissions are estimated to be 64.8 CO2eq of which 0 percents were directly offset. Estimations were conducted using the MachineLearning Impact calculator. Citation BibTeX: Model Card Contact PyThaiNLP
$-/run
173
Huggingface
wangchanglm-7.5B-sft-en-sharded
wangchanglm-7.5B-sft-en-sharded
Model Card for WangChanGLM 🐘 - The Multilingual Instruction-Following Model WangChanGLM is a multilingual, instruction-finetuned Facebook XGLM-7.5B using open-source, commercially permissible datasets (LAION OIG chip2 and infill_dbpedia, DataBricks Dolly v2, OpenAI TL;DR, and Hello-SimpleAI HC3; about 400k examples), released under CC-BY SA 4.0. The models are trained to perform a subset of instruction-following tasks we found most relevant namely: reading comprehension, brainstorming, and creative writing. We provide the weights for a model finetuned on an English-only dataset (wangchanglm-7.5B-sft-en) and another checkpoint further finetuned on Google-Translated Thai dataset (wangchanglm-7.5B-sft-enth). We perform Vicuna-style evaluation using both humans and ChatGPT (in our case, gpt-3.5-turbo since we are still on the waitlist for gpt-4) and observe some discrepancies between the two types of annoators. All training and evaluation codes are shared under the Apache-2.0 license in our Github, as well as datasets and model weights on HuggingFace. In a similar manner to Dolly v2, we use only use open-source, commercially permissive pretrained models and datasets, our models are neither restricted by non-commercial clause like models that use LLaMA as base nor non-compete clause like models that use self-instruct datasets from ChatGPT. See our live demo here. Developed by: PyThaiNLP and VISTEC-depa AI Research Institute of Thailand Model type: Finetuned XGLM-7.5B Language(s) (NLP): en, th, ja, vi capacibilities evaluated, theoretically all 30 languages of XGLM-7.5B License: CC-BY SA 4.0 Model Sources Repository: pythainlp/wangchanglm Blog: Medium Demo: Colab notebook Uses Direct Use Intended to be use as an instruction-following model for reading comprehension, brainstorming and creative writing. Downstream Use The model can be finetuned for any typical instruction-following use cases. Out-of-Scope Use We do not expect the models to perform well in math problems, reasoning, and factfulness. We intentionally filter out training examples from these use cases. Bias, Risks, and Limitations We noticed similar limitations to other finetuned instruction followers such as math problems, reasoning, and factfulness. Even though the models do not perform on the level that we expect them to be abused, they do contain undesirable biases and toxicity and should be further optimized for your particular use cases. Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. How to Get Started with the Model Use the code below to get started with the model. Training Details Training Data Finetuning datasets are sourced from LAION OIG chip2 and infill_dbpedia (Apache-2.0), DataBricks Dolly v2 (Apache-2.0), OpenAI TL;DR (MIT), and Hello-SimpleAI HC3 (CC-BY SA). Training Procedure See pythainlp/wangchanglm. Training regime: LoRA with 4 GPUs. See more details at pythainlp/wangchanglm. Evaluation We performed automatic evaluation in the style of Vicuna and human evaluation. See more details from our blog. Environmental Impact Experiments were conducted using a private infrastructure, which has a carbon efficiency of 0.432 kgCO2eq/kWh. A cumulative of 500 hours of computation was performed on hardware of type Tesla V100-SXM2-32GB (TDP of 300W). Total emissions are estimated to be 64.8 CO2eq of which 0 percents were directly offset. Estimations were conducted using the MachineLearning Impact calculator. Citation BibTeX: Model Card Contact PyThaiNLP
$-/run
163
Huggingface
wangchanglm-7.5B-sft-en-8bit-sharded
$-/run
137
Huggingface
han-coref-v1.0
han-coref-v1.0
🪿 Han-Coref: Thai Coreference resolution by PyThaiNLP (Model) This project want to create Thai Coreference resolution system. This project is developed by 🪿 Wannaphong Phatthiyaphaibun. Current 🪿 Han-Coref version: 1.0 GitHub: pythainlp/han-coref Model: pythainlp/han-coref-v1.0 Dataset: pythainlp/han-corf-dataset-v1.0 Cite as or BibTeX entry: License All source code use Apache License Version 2.0. The Dataset use Creative Commons Attribution 3.0 Unported License. This project is a part of 🪿 PyThaiNLP project. We build Thai NLP. PyThaiNLP
$-/run
15
Huggingface
wangchanglm-7.5B-sft-en-8bit
wangchanglm-7.5B-sft-en-8bit
Platform did not provide a description for this model.
$-/run
2
Huggingface
adapter-wangchanglm-7.5B-sft-en-klongklon
adapter-wangchanglm-7.5B-sft-en-klongklon
Model Card for Klongklon Adapter of WangChanGLM 🐘 This is a LoRA adapter for Thai poems trained on 80k poems to be used with WangChanGLM. WangChanGLM is a multilingual, instruction-finetuned Facebook XGLM-7.5B using open-source, commercially permissible datasets (LAION OIG chip2 and infill_dbpedia, DataBricks Dolly v2, OpenAI TL;DR, and Hello-SimpleAI HC3; about 400k examples), released under CC-BY SA 4.0. The models are trained to perform a subset of instruction-following tasks we found most relevant namely: reading comprehension, brainstorming, and creative writing. We provide the weights for a model finetuned on an English-only dataset (wangchanglm-7.5B-sft-en) and another checkpoint further finetuned on Google-Translated Thai dataset (wangchanglm-7.5B-sft-enth). We perform Vicuna-style evaluation using both humans and ChatGPT (in our case, gpt-3.5-turbo since we are still on the waitlist for gpt-4) and observe some discrepancies between the two types of annoators. All training and evaluation codes are shared under the Apache-2.0 license in our Github, as well as datasets and model weights on HuggingFace. In a similar manner to Dolly v2, we use only use open-source, commercially permissive pretrained models and datasets, our models are neither restricted by non-commercial clause like models that use LLaMA as base nor non-compete clause like models that use self-instruct datasets from ChatGPT. Developed by: PyThaiNLP and VISTEC-depa AI Research Institute of Thailand Model type: Finetuned XGLM-7.5B Language(s) (NLP): en, th, ja, vi capacibilities evaluated, theoretically all 30 languages of XGLM-7.5B License: CC-BY SA 4.0 Model Sources Repository: pythainlp/wangchanglm Blog: Medium Demo: Colab notebook Uses Direct Use Intended to be use as an instruction-following model for reading comprehension, brainstorming and creative writing. Downstream Use The model can be finetuned for any typical instruction-following use cases. Out-of-Scope Use We do not expect the models to perform well in math problems, reasoning, and factfulness. We intentionally filter out training examples from these use cases. Bias, Risks, and Limitations We noticed similar limitations to other finetuned instruction followers such as math problems, reasoning, and factfulness. Even though the models do not perform on the level that we expect them to be abused, they do contain undesirable biases and toxicity and should be further optimized for your particular use cases. Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. How to Get Started with the Model See example notebook. Training Details Training Data Finetuned on PythaiNLP/klongklon Training Procedure See pythainlp/wangchanglm. Training regime: LoRA with 4 GPUs. See more details at pythainlp/wangchanglm. Evaluation We performed automatic evaluation in the style of Vicuna and human evaluation. See more details from our blog. Environmental Impact Experiments were conducted using a private infrastructure, which has a carbon efficiency of 0.432 kgCO2eq/kWh. A cumulative of 500 hours of computation was performed on hardware of type Tesla V100-SXM2-32GB (TDP of 300W). Total emissions are estimated to be 64.8 CO2eq of which 0 percents were directly offset. Estimations were conducted using the MachineLearning Impact calculator. Citation BibTeX: Model Card Contact PyThaiNLP
$-/run
0
Huggingface
onnx_lst20ner
$-/run
0
Huggingface