calme-2.2-qwen2-7b/README.md

---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- chat
- qwen
- qwen2
- finetune
- chatml
- OpenHermes-2.5
- HelpSteer2
- Orca
- SlimOrca
base_model: Qwen/Qwen2-7B
datasets:
- nvidia/HelpSteer2
- teknium/OpenHermes-2.5
- microsoft/orca-math-word-problems-200k
- Open-Orca/SlimOrca
model_name: calme-2.2-qwen2-7b
pipeline_tag: text-generation
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
model-index:
- name: calme-2.2-qwen2-7b
  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: 35.97
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
      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: 33.11
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
      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: 19.34
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
      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: 5.48
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
      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: 13.28
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
      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: 32.21
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
      name: Open LLM Leaderboard
---

<img src="./qwen2-fine-tunes-maziyar-panahi.webp" alt="Qwen2 fine-tune" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

# MaziyarPanahi/calme-2.2-qwen2-7b

This is a fine-tuned version of the `Qwen/Qwen2-7B` model. It aims to improve the base model across all benchmarks.

# ⚡ Quantized GGUF

All GGUF models are available here: [MaziyarPanahi/calme-2.2-qwen2-7b-GGUF](https://huggingface.co/MaziyarPanahi/calme-2.2-qwen2-7b-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-2.2-qwen2-7b)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |23.23|
|IFEval (0-Shot)    |35.97|
|BBH (3-Shot)       |33.11|
|MATH Lvl 5 (4-Shot)|19.34|
|GPQA (0-shot)      | 5.48|
|MuSR (0-shot)      |13.28|
|MMLU-PRO (5-shot)  |32.21|




# 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-2.2-qwen2-7b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.2-qwen2-7b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.2-qwen2-7b")
```