|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: Johnsnowlabs/PhiMerge-2.7B-Dare |
|
tags: |
|
- generated_from_trainer |
|
- Phi |
|
- axolotl |
|
- instruct |
|
- finetune |
|
- chatml |
|
- gpt4 |
|
- synthetic data |
|
- distillation |
|
model-index: |
|
- name: PhiMerge-2.7B-Dare-daser |
|
results: [] |
|
datasets: |
|
- argilla/distilabel-capybara-dpo-7k-binarized |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
--- |
|
<!-- 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. --> |
|
|
|
# PhiMerge-2.7B-Dare-daser |
|
 |
|
|
|
PhiMerge-2.7B-Dare-daser is a mixture of two techniques that are LaserQlora and Dora. This model is a DPO fine-tuned of [johnsnowlabs/PhiMerge-2.7B-Dare](https://huggingface.co/johnsnowlabs/PhiMerge-2.7B-Dare) using the [argilla/distilabel-capybara-dpo-7k-binarized](https://huggingface.co/datasets/argilla/distilabel-capybara-dpo-7k-binarized) preference dataset. The model has been trained on top 16 projections (q_proj, k_proj, v_proj) based on snr values. This model has been trained for 1080 steps. |
|
|
|
## 🏆 Evaluation results |
|
|
|
#### Coming Soon |
|
|
|
## Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "johnsnowlabs/PhiMerge-2.7B-Dare-daser" |
|
messages = [{"role": "user", "content": "Explain what is Machine learning."}] |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
) |
|
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
|
|
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-04 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: paged_adamw_32bit |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 1080 |
|
|
|
### LoRA Config |
|
- lora_r: 16 |
|
- lora_alpha: 32 |
|
- lora_dropout: 0.05 |
|
- peft_use_dora: true |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0.dev0 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.0 |
