Update README.md

README.md

@@ -1,3 +1,145 @@
 ---
 license: apache-2.0
+datasets:
+- argilla/ultrafeedback-binarized-preferences
+language:
+- de
+tags:
+- dpo
+- alignment-handbook
 ---
+<div align="center">
+<img src=https://cdn-uploads.huggingface.co/production/uploads/6474c16e7d131daf633db8ad/-mL8PSG00X2lEw1lb8E1Q.png>
+</div>
+
+# Model Card for Phoenix
+
+Phoenixis a model trained using Direct Preference Optimization (DPO). This model is the first version, which has been trained following the process of the Alignment-Handbook from Huggingface. 
+
+In contrast to zephyr and notus this model has been trained using german instruction and dpo-data. In detail, a German translation of HuggingFaceH4/ultrachat_200k
+
+and HuggingFaceH4/ultrafeedback_binarized was created in addition to a series of instruction datasets. The LLM haoranxu/ALMA-13B was used for this. 
+
+While the mistral model performs really well, it is not really suitable for the german language. Therefore we have used the fantastic LeoLM/leo-mistral-hessianai-7b.
+
+Thanks to the new type of training, Phoenix is not only able to compete with the Mistral model from LeoLM but also **beats the Llama-70b-chat model in 2 mt-bench categories**
+
+This model **wouldn't have been possible without the amazing work of Huggingface, LeoLM, openbnb, Argilla the Alma-Team and many others of the AI community**
+
+## MT-Bench-DE Scores
+
+## Model Details
+
+### Model Description
+
+- **Developed by:** Matthias Uhlig (based on HuggingFace H4, Argillla and MistralAI previous efforts and amazing work)
+- **Shared by:** Matthias Uhlig
+- **Model type:** GPT-like 7B model DPO fine-tuned
+- **Language(s) (NLP):** German
+- **License:** Apache 2.0 (same as alignment-handbook/zephyr-7b-dpo-full)
+- **Finetuned from model:** [`LeoLM/leo-mistral-hessianai-7b`](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b)
+
+### Model Sources
+
+- **Repository:** -
+- **Paper:** in progress
+- **Demo:** -
+
+## Training Details
+
+### Training Hardware
+
+We used a VM with 8 x A100 80GB hosted in Runpods.io.
+
+### Training Data
+
+We used a a new translated version of [`HuggingFaceH4/ultrachat_200k`](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k), and [argilla/ultrafeedback-binarized-preferences](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences).
+
+The data used for training will be made public after additional quality inspection.
+
+## Prompt template
+We use the same prompt template as [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta):
+```
+<|system|>
+</s>
+<|user|>
+{prompt}</s>
+<|assistant|>
+```
+
+It is also possible to use the model in a multi-turn setup
+```
+<|system|>
+</s>
+<|user|>
+{prompt_1}</s>
+<|assistant|>
+{answer_1}</s>
+<|user|>
+{prompt_2}</s>
+<|assistant|>
+```
+
+## Usage
+You will first need to install `transformers` and `accelerate` (just to ease the device placement), then you can run any of the following:
+### Via `generate`
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("DRXD1000/Phoenix", torch_dtype=torch.bfloat16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("DRXD1000/Phoenix")
+prompt = """<|system|>
+</s>
+<|user|>
+Erkläre mir was KI ist.</s>
+<|assistant|>
+"""
+inputs = tokenizer.apply_chat_template(prompt,  return_tensors="pt").to("cuda")
+outputs = model.generate(inputs, num_return_sequences=1, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```
+
+## Ethical Considerations and Limitations
+ 
+As with all LLMs, the potential outputs of `DRXD1000/Phoenix` cannot be predicted
+
+in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses
+
+to user prompts. Therefore, before deploying any applications of `DRXD1000/Phoenix`, developers should
+
+perform safety testing and tuning tailored to their specific applications of the model.
+
+Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
+
+
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1
+
+
+
+
+