create model card

README.md

@@ -4,12 +4,27 @@ tags:
 - axolotl
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- allenai/ai2_arc
+- camel-ai/physics
+- camel-ai/chemistry
+- camel-ai/biology
+- metaeval/reclor
+- openbookqa
+- mandyyyyii/scibench
+- derek-thomas/ScienceQA
+- wenhu/TheoremQA
+- TIGER-Lab/ScienceEval
 ---
 
-<!-- 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. -->
+# 🔬 Einstein-7B
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on datasets related to science.
+
+This model is fine-tuned using [QLoRa](https://arxiv.org/abs/2305.14314) and [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
+
+This model's training was sponsored by [sablo.ai](https://sablo.ai).
 
-[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 <details><summary>See axolotl config</summary>
 
 axolotl version: `0.3.0`
@@ -137,59 +152,54 @@ special_tokens:
 
 </details><br>
 
-# science-mistral
+# 📊 Datasets
+
+Following datasets were used in this model:
+
+- [ARC](https://huggingface.co/datasets/allenai/ai2_arc) (Note: Only **train** part)
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+- [camel-ai/physics](https://huggingface.co/datasets/camel-ai/physics)
 
-## Model description
+- [camel-ai/chemistry](https://huggingface.co/datasets/camel-ai/chemistry)
 
-More information needed
+- [camel-ai/biology](https://huggingface.co/datasets/camel-ai/biology)
 
-## Intended uses & limitations
+- [openbookqa](https://huggingface.co/datasets/openbookqa)
 
-More information needed
+- [reclor](https://huggingface.co/datasets/metaeval/reclor)
 
-## Training and evaluation data
+- [scibench](https://github.com/mandyyyyii/scibench)
 
-More information needed
+- [ScienceQA](https://huggingface.co/datasets/derek-thomas/ScienceQA)
 
-## Training procedure
+- [TheoremQA](https://huggingface.co/datasets/wenhu/TheoremQA)
 
+- [ScienceEval](https://huggingface.co/datasets/TIGER-Lab/ScienceEval)
 
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
+# 💬 Prompt Template
 
-### Training hyperparameters
+You can use this prompt template while using the model:
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 6
-- eval_batch_size: 6
-- seed: 42
-- gradient_accumulation_steps: 12
-- total_train_batch_size: 72
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 10
-- num_epochs: 2
+### Alpaca
+
+```
+Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{instruction}
+
+### Input:
+{input}
+
+### Response:
+```
 
-### Training results
+# 🤝 Acknowledgments
 
+Thanks to Platypus for providing scripts to convert some of the datasets to Alpaca format: [Platypus/data_pipeline](https://github.com/arielnlee/Platypus/tree/main/data_pipeline)
 
+Thanks to all the dataset authors mentioned in the datasets section.
 
-### Framework versions
+Thanks to [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) for making the repository I used to make this model.
 
-- PEFT 0.7.0
-- Transformers 4.37.0
-- Pytorch 2.0.1+cu118
-- Datasets 2.16.1
-- Tokenizers 0.15.0
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)