good readme

README.md

@@ -1,15 +1,66 @@
 ---
+language:
+- en
 license: other
 tags:
 - axolotl
 - generated_from_trainer
+- phi
+- phi2
+- einstein
+- instruct
+- finetune
+- chatml
+- gpt4
+- synthetic data
+- science
+- physics
+- chemistry
+- biology
+- math
 base_model: Qwen/Qwen1.5-32B
+datasets:
+- allenai/ai2_arc
+- camel-ai/physics
+- camel-ai/chemistry
+- camel-ai/biology
+- camel-ai/math
+- metaeval/reclor
+- openbookqa
+- mandyyyyii/scibench
+- derek-thomas/ScienceQA
+- TIGER-Lab/ScienceEval
+- jondurbin/airoboros-3.2
+- LDJnr/Capybara
+- Cot-Alpaca-GPT4-From-OpenHermes-2.5
+- STEM-AI-mtl/Electrical-engineering
+- knowrohit07/saraswati-stem
+- sablo/oasst2_curated
+- glaiveai/glaive-code-assistant
+- lmsys/lmsys-chat-1m
+- TIGER-Lab/MathInstruct
+- bigbio/med_qa
+- meta-math/MetaMathQA-40K
+- openbookqa
+- piqa
+- metaeval/reclor
+- derek-thomas/ScienceQA
+- scibench
+- sciq
+- Open-Orca/SlimOrca
+- migtissera/Synthia-v1.3
+- TIGER-Lab/ScienceEval
 ---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/VTacthtA6N97SqD23WtwB.png)
 
-<!-- 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-v4-Qwen-1.5-32B
+
+This model is a [QLoRA](https://arxiv.org/abs/2305.14314) fine-tuned version of [Qwen/Qwen1.5-32B](https://huggingface.co/Qwen/Qwen1.5-32B) on diverse datasets.
+
+This model is finetuned using `8xRTX3090` + `1xRTXA6000` using [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: `0.4.0`
@@ -121,54 +172,78 @@ special_tokens:
   unk_token: "<unk>"
 tokens:
   - "<|im_start|>"
+```
+</details><br>
+
+# 💬 Prompt Template
+
+You can use this prompt template while using the model:
+
+### ChatML
 
+```
+<|im_start|>system
+{system}<|im_end|>
+<|im_start|>user
+{user}<|im_end|>
+<|im_start|>assistant
+{asistant}<|im_end|>
 ```
 
-</details><br>
+This prompt template is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
+`tokenizer.apply_chat_template()` method:
 
-# Einstein-v4-Qwen-1.5-32B
+```python
+messages = [
+    {"role": "system", "content": "You are helpful AI asistant."},
+    {"role": "user", "content": "Hello!"}
+]
+gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
+model.generate(**gen_input)
+```
 
-This model is a fine-tuned version of [Qwen/Qwen1.5-32B](https://huggingface.co/Qwen/Qwen1.5-32B) on the None dataset.
+# 🔄 Quantizationed versions
 
-## Model description
+Quantizationed versions of this model is currently not available.
 
-More information needed
+# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Einstein-v4-Qwen-1.5-32B)
 
-## Intended uses & limitations
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.54|
+|AI2 Reasoning Challenge (25-Shot)|62.37|
+|HellaSwag (10-Shot)              |83.85|
+|MMLU (5-Shot)                    |74.04|
+|TruthfulQA (0-shot)              |58.86|
+|Winogrande (5-shot)              |80.43|
+|GSM8k (5-shot)                   |51.71|
 
-More information needed
 
-## Training and evaluation data
+# 🤖 Additional information about training
 
-More information needed
+This model is full fine-tuned for 2 epochs. 
 
-## Training procedure
+Total number of steps was 3352.
 
-### Training hyperparameters
+<details><summary>Loss graph</summary>
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 9
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 36
-- total_eval_batch_size: 9
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 10
-- num_epochs: 2
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/0Vp8iDmXi4-XbQCiwQtNP.png)
+
+</details><br>
 
-### Training results
+# 🤝 Acknowledgments
 
+Thanks to [sablo.ai](https://sablo.ai) for sponsoring this model.
 
+Thanks to all the dataset authors mentioned in the datasets section.
+
+Thanks to [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) for making the repository I used to make this model.
+
+Thanks to all open source AI community.
+
+[<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)
 
-### Framework versions
+If you would like to support me:
 
-- PEFT 0.10.0
-- Transformers 4.40.0.dev0
-- Pytorch 2.1.2+cu118
-- Datasets 2.18.0
-- Tokenizers 0.15.0
+[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)