README.md

---
language:
- fr
- en
license: other
library_name: transformers
tags:
- chat
- qwen
- qwen2.5
- finetune
- french
- english
base_model: Qwen/Qwen2.5-3B
datasets:
- MaziyarPanahi/french_instruct_sharegpt
- arcee-ai/EvolKit-20k
model_name: calme-3.3-instruct-3b
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE
pipeline_tag: text-generation
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
model-index:
- name: calme-3.3-instruct-3b
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 64.23
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.3-instruct-3b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 25.68
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.3-instruct-3b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 0.0
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.3-instruct-3b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 4.36
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.3-instruct-3b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 9.4
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.3-instruct-3b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 25.62
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.3-instruct-3b
      name: Open LLM Leaderboard
---

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

> [!TIP]
> This is avery small 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-3.3-instruct-3b

This model is an advanced iteration of the powerful `Qwen/Qwen2.5-3B`, specifically fine-tuned to enhance its capabilities in generic domains.


# ⚡ Quantized GGUF

All GGUF models are available here: [MaziyarPanahi/calme-3.3-instruct-3b-GGUF](https://huggingface.co/MaziyarPanahi/calme-3.3-instruct-3b-GGUF)


# 🏆 [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_MaziyarPanahi__calme-3.3-instruct-3b)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |21.55|
|IFEval (0-Shot)    |64.23|
|BBH (3-Shot)       |25.68|
|MATH Lvl 5 (4-Shot)| 0.00|
|GPQA (0-shot)      | 4.36|
|MuSR (0-shot)      | 9.40|
|MMLU-PRO (5-shot)  |25.62|


# Prompt Template

This model uses `ChatML` prompt template:

```
<|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-3.3-instruct-3b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.3-instruct-3b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.3-instruct-3b")
```



# 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.