|
--- |
|
tags: |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
- rhysjones/phi-2-orange |
|
- cognitivecomputations/dolphin-2_6-phi-2 |
|
- Microsoft/Phi-2 |
|
base_model: |
|
- rhysjones/phi-2-orange |
|
- cognitivecomputations/dolphin-2_6-phi-2 |
|
license: mit |
|
--- |
|
|
|
# Phiter |
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/6493317e9621f988db6c469c/ZjXk8XIDt00E2n6j4brQW.png" alt="Phiter Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/> |
|
|
|
Phiter is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
|
* [rhysjones/phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange) |
|
* [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2) |
|
|
|
Thanks to the great [Maxime Labonne](https://huggingface.co/mlabonne) we have evaluation results on [YALL](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard). |
|
|
|
The model tops all other phi-2 finetunes on the leaderboard, even most MoE implementations like Phixtral(Date: 27th February 2024) |
|
|
|
License: MIT |
|
|
|
This model wouldn't have been possible without the support of: |
|
|
|
[Maxime Labonne](https://huggingface.co/mlabonne) - he helped me troubleshoot the merge process |
|
|
|
[brittlewis12](https://huggingface.co/brittlewis12) - helped me troubleshooting the creation of GGUF files |
|
|
|
|
|
|
|
<!-- prompt-template start --> |
|
## Prompt template: ChatML |
|
|
|
``` |
|
<|im_start|>system |
|
{system_message}<|im_end|> |
|
<|im_start|>user |
|
{prompt}<|im_end|> |
|
<|im_start|>assistant |
|
|
|
``` |
|
|
|
<!-- prompt-template end --> |
|
|
|
GGUF: [Phiter-GGUF](https://huggingface.co/Venkman42/Phiter-GGUF/) |
|
|
|
## 🧩 Configuration |
|
|
|
```yaml |
|
models: |
|
- model: mixedbread-ai/phi-2 |
|
# no parameters necessary for base model |
|
- model: rhysjones/phi-2-orange |
|
parameters: |
|
density: 0.5 |
|
weight: 0.5 |
|
- model: cognitivecomputations/dolphin-2_6-phi-2 |
|
parameters: |
|
density: 0.5 |
|
weight: 0.3 |
|
merge_method: ties |
|
base_model: mixedbread-ai/phi-2 |
|
parameters: |
|
normalize: true |
|
dtype: float16 |
|
|
|
``` |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "Venkman42/Phiter" |
|
messages = [{"role": "user", "content": "What is a large language model?"}] |
|
|
|
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"]) |
|
``` |
