---
license: other
language:
- en
base_model:
- meta-llama/Meta-Llama-3.1-8B-Instruct
pipeline_tag: text-generation
inference: true
library_name: transformers
datasets:
- mlabonne/orca-agentinstruct-1M-v1-cleaned
- HuggingFaceTB/smoltalk
- Magpie-Align/Magpie-Qwen2.5-Pro-300K-Filtered
- Magpie-Align/Magpie-Qwen2-Pro-200K-Chinese
- O1-OPEN/OpenO1-SFT
---

> [!TIP]
> This is an experimental model, so it might not perform well for some prompts and may be sensitive to hyper parameters.
> It is mainly trained to enhance reasoning capabilities.

# khulaifi95/Llama-3.1-8B-Reason-Blend-888k


# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_khulaifi95__Llama-3.1-8B-Reason-Blend-888k)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |     |
|IFEval (0-Shot)    |     |
|BBH (3-Shot)       |     |
|MATH Lvl 5 (4-Shot)|     |
|GPQA (0-shot)      |     |
|MuSR (0-shot)      |     |
|MMLU-PRO (5-shot)  |     |

# Prompt Template

This model uses `ChatML` prompt template:

```sh
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are Llama Reason Blend, a helpful AI assistant.<|eot_id|>
<|start_header_id|>user<|end_header_id|>
Hello Llama Reason Blend, what can you do for me?<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
````

# 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="khulaifi95/Llama-3.1-8B-Reason-Blend-888k")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("khulaifi95/Llama-3.1-8B-Reason-Blend-888k")
model = AutoModelForCausalLM.from_pretrained("khulaifi95/Llama-3.1-8B-Reason-Blend-888k")
```

# 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.