Hugging Face's logo

rombodawg
/
Rombos-LLM-V2.5-Qwen-32b-Exl2-4.25-bit

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Rombos-LLM-V2.5-Qwen-32b-Exl2-4.25-bit / README.md
rombodawg's picture
rombodawg
Update README.md
7426483 verified
preview code
|
raw
history blame contribute delete
1.06 kB
metadata
library_name: transformers
base_model:
  - Qwen/Qwen2.5-32B-Instruct
license: apache-2.0

Rombos-LLM-V2.5-Qwen-32b

image/jpeg

Here are the best params to use for this model, and possibly other qwen models in the oobagooba text generation web ui. From my testing at least:

image/png

Rombos-LLM-V2.5-Qwen-32b is a continues finetuned version of Qwen2.5-32B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the Ties merge method

This version of the model shows higher performance than the original instruct and base models.

Quants: (Coming soon)

GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF

EXL2:

Benchmarks: (Coming soon)