Update README.md

README.md

@@ -2,30 +2,29 @@
 tags:
 - generated_from_trainer
 model-index:
-- name: starcoderplus-ift-v41
+- name: starchat-beta
   results: []
+license: bigcode-openrail-m
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 
-# starcoderplus-ift-v41
+<img src="https://huggingface.co/spaces/HuggingFaceH4/starchat-playground/resolve/main/thumbnail.png" alt="BigScience Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
 
-This model is a fine-tuned version of [bigcode-data/starcoderplus](https://huggingface.co/bigcode-data/starcoderplus) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4720
+# Model Card for StarChat Beta
 
-## Model description
+StarChat is a series of language models that are trained to act as helpful coding assistants. StarChat Beta is the second model in the series, and is a fine-tuned version of [StarCoderPlus](https://huggingface.co/bigcode/starcoderplus) that was trained on an ["uncensored"](https://erichartford.com/uncensored-models) variant of the [`openassistant-guanaco` dataset](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). We found that removing the in-built alignment of the OpenAssistant dataset boosted performance on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) and made the model more helpful at coding tasks. However, this means that model is likely to generate problematic text when prompted to do so and should only be used for educational and research purposes.
+
+- **Repository:** [bigcode-project/starcoder](https://github.com/bigcode-project/starcoder)
+- **Languages:** 35+ Natural languages & 80+ Programming languages
 
-More information needed
 
 ## Intended uses & limitations
 
-More information needed
+The model was fine-tuned on a variant of the [`OpenAssistant/oasst1`](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset, which contains a diverse range of dialogues in over 35 languages. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/starchat-playground) to test its coding capabilities. 
 
 ## Training and evaluation data
 
-More information needed
+StarChat Beta is trained on an ["uncensored"](https://erichartford.com/uncensored-models) variant of the [`openassistant-guanaco` dataset](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). We applied the same [recipe](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered/blob/main/wizardlm_clean.py) used to filter the ShareGPT datasets behind the [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered).
 
 ## Training procedure
 
@@ -63,4 +62,4 @@ The following hyperparameters were used during training:
 - Transformers 4.28.1
 - Pytorch 2.0.1+cu118
 - Datasets 2.12.0
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3