Kotokin/Magnum-v1-72b-Qwen2.5-5bpw

Magnum-v1-72b-Qwen2.5

A merge of the OG QwenV2-based anthracite-org/magnum-v1-72b with the new Qwen/Qwen2.5-72B-Instruct

Model Details

• Base Model: Qwen/Qwen2.5-72B-Instruct
• Influence Model: anthracite-org/magnum-v1-72b
• Method: LoRA extraction from Magnum-v1 and then applied to Qwen2.5-Instruct

Process

1. A LoRA was extracted from anthracite-org/magnum-v1-72b and Qwen/Qwen2-72B-Instruct
2. This LoRA was then applied to Qwen/Qwen2.5-72B-Instruct.
3. The resulting model was merged to create this standalone version.

Prompt Template

"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""

Results

It seems to have worked in my testing. Just as "creative" as the OG magnum-v1, and seems to have retained the improvements of Qwen2.5 (eg. it can zero-shot code a snake game in python and is aware of world events which happened after QwenV2 released)