---
base_model:
- NousResearch/Hermes-3-Llama-3.1-8B
- Replete-AI/Replete-LLM-V2-Llama-3.1-8b
tags:
- merge
- mergekit
- lazymergekit
- NousResearch/Hermes-3-Llama-3.1-8B
- Replete-AI/Replete-LLM-V2-Llama-3.1-8b
---

# Replete-LLM-V3-Llama-3.1-8b

Replete-LLM-V3-Llama-3.1-8b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Etherll/Replete-LLM-V3-Llama-3.1-8b-merged](https://huggingface.co/Etherll/Replete-LLM-V3-Llama-3.1-8b-merged)
* [Replete-AI/Replete-LLM-V2-Llama-3.1-8b](https://huggingface.co/Replete-AI/Replete-LLM-V2-Llama-3.1-8b)

## 🧩 Configuration

```yaml
models:
  - model: NousResearch/Hermes-3-Llama-3.1-8B
    parameters:
      weight: 1
  - model: Replete-AI/Replete-LLM-V2-Llama-3.1-8b
    parameters:
      weight: 1
merge_method: ties
base_model: rombodawg/Meta-Llama-3.1-8B-reuploaded
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Etherll/Replete-LLM-V3-Llama-3.1-8b"
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"])
```