Fine-Tuned
Collection
41 items
β’
Updated
β’
6
This is a fine-tuned version of the Qwen/Qwen2-7B
model. It aims to improve the base model across all benchmarks.
All GGUF models are available here: MaziyarPanahi/calme-2.7-qwen2-7b-GGUF
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 22.07 |
IFEval (0-Shot) | 35.92 |
BBH (3-Shot) | 28.91 |
MATH Lvl 5 (4-Shot) | 12.08 |
GPQA (0-shot) | 5.48 |
MuSR (0-shot) | 19.94 |
MMLU-PRO (5-shot) | 30.06 |
This model uses ChatML
prompt template:
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
# 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-2.7-qwen2-7b")
pipe(messages)
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.7-qwen2-7b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.7-qwen2-7b")