AI-M3-10.7Bv2 / README.md
sydonayrex's picture
Upload folder using huggingface_hub
75fadee verified
|
raw
history blame
1.42 kB
---
tags:
- merge
- mergekit
- lazymergekit
- mistralai/Mistral-7B-Instruct-v0.3
base_model:
- mistralai/Mistral-7B-Instruct-v0.3
---
# AI-M3-10.7Bv2
AI-M3-10.7Bv2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
## 🧩 Configuration
```yaml
dtype: float16
base_model: mistralai/Mistral-7B-Instruct-v0.3
merge_method: task_arithmetic
slices:
- sources:
- model: mistralai/Mistral-7B-Instruct-v0.3
layer_range: [0, 26]
- sources:
- model: mistralai/Mistral-7B-Instruct-v0.3
layer_range: [10, 32]
parameters:
t: 1
weight: 1.0
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "sydonayrex/AI-M3-10.7Bv2"
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"])
```