---
license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- chat
- qwen
- qwen2.5
- finetune
- english
library_name: transformers
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
base_model: MaziyarPanahi/calme-3-selfmerge-qwen2-78b
model_name: calme-3.1-instruct-78b
---

<img src="./calme_3.png" alt="Calme-3 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

> [!TIP]
> This is an experimental model, so it might not perform well for some prompts and may be sensitive to hyper parameters. I would appreciate any feedback to see if I can fix any issues in the next iteration. ❤️

# MaziyarPanahi/calme-3.1-instruct-78b

This model is an advanced iteration of the powerful `Qwen/Qwen2.5-72B`, specifically fine-tuned to enhance its capabilities in generic domains. The `Qwen2.5-72B` base model was merged with itself to create a larger model. After that, the model was fine-tuned on a custom datasets.

# ⚡ Quantized GGUF

Thanks to `mradermacher`: [calme-3.1-instruct-78b-GGUF](mradermacher/calme-3.1-instruct-78b-GGUF)

# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)

Leaderboard 2 coming soon!

# Prompt Template

This model uses `ChatML` prompt template:

```sh
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
````

# How to use

```python

# Use a pipeline as a high-level helper

from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-3.1-instruct-78b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.1-instruct-78b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.1-instruct-78b")
```

# Ethical Considerations

As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.