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-3.2-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

Here are the GGUF models thanks to https://huggingface.co/bartowski: calme-3.2-instruct-78b-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.02
IFEval (0-Shot)	80.63
BBH (3-Shot)	62.61
MATH Lvl 5 (4-Shot)	39.95
GPQA (0-shot)	20.36
MuSR (0-shot)	38.53
MMLU-PRO (5-shot)	70.03

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

# 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-3.2-instruct-78b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.2-instruct-78b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.2-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.