README.md

---
tags:
- merge
- mergekit
- lazymergekit
- hfl/llama-3-chinese-8b-instruct-v2
- NousResearch/Hermes-2-Theta-Llama-3-8B
base_model:
- hfl/llama-3-chinese-8b-instruct-v2
- NousResearch/Hermes-2-Theta-Llama-3-8B
- hfl/llama-3-chinese-8b-instruct-v2
- NousResearch/Hermes-2-Theta-Llama-3-8B
- hfl/llama-3-chinese-8b-instruct-v2
---

# Llama3-15B-lingyang-v0.1

Llama3-15B-lingyang-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [hfl/llama-3-chinese-8b-instruct-v2](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2)
* [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B)
* [hfl/llama-3-chinese-8b-instruct-v2](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2)
* [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B)
* [hfl/llama-3-chinese-8b-instruct-v2](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: "hfl/llama-3-chinese-8b-instruct-v2"
        layer_range: [0, 10]
  - sources:
      - model: "NousResearch/Hermes-2-Theta-Llama-3-8B"
        layer_range: [0, 20]
  - sources:
      - model: "hfl/llama-3-chinese-8b-instruct-v2"
        layer_range: [10, 20]
  - sources:
      - model: "NousResearch/Hermes-2-Theta-Llama-3-8B"
        layer_range: [20, 32]
  - sources:
      - model: "hfl/llama-3-chinese-8b-instruct-v2"
        layer_range: [20, 32]

merge_method: passthrough
base_model: "NousResearch/Hermes-2-Theta-Llama-3-8B"
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "wwe180/Llama3-15B-lingyang-v0.1"
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"])
```