gate369's picture
Upload folder using huggingface_hub
1400174 verified
|
raw
history blame
1.71 kB
---
base_model:
- liminerity/Bitnet-Mistral.0.2-v3
- liminerity/Bitnet-Mistral.0.2-v2
tags:
- merge
- mergekit
- lazymergekit
- liminerity/Bitnet-Mistral.0.2-v3
- liminerity/Bitnet-Mistral.0.2-v2
---
# Bitnet-Mistral-1-and-2-slerp
Bitnet-Mistral-1-and-2-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [liminerity/Bitnet-Mistral.0.2-v3](https://huggingface.co/liminerity/Bitnet-Mistral.0.2-v3)
* [liminerity/Bitnet-Mistral.0.2-v2](https://huggingface.co/liminerity/Bitnet-Mistral.0.2-v2)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: liminerity/Bitnet-Mistral.0.2-v3
layer_range: [0, 24]
- model: liminerity/Bitnet-Mistral.0.2-v2
layer_range: [0, 24]
merge_method: slerp
base_model: liminerity/Bitnet-Mistral.0.2-v3
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "gate369/Bitnet-Mistral-1-and-2-slerp"
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"])
```