Downloads · 30 days
46
5% of all-time downloads
alwaysgood/qwen35_sft_023_dpo-GGUF
qwen35_sft_023_dpo-GGUF is a image-text-to-text model from alwaysgood. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for llama.cpp. The card lists the license as other.
GGUF conversion of alwaysgood/qwen35sft023dpo for llama.cpp and LM Studio.
Downloads · 30 days
46
5% of all-time downloads
All-time downloads
872
Public
Repo size
23.6 GB
Likes
0
Public
Click a slice to open those files.
.gguf11.8 GB · 100%
From the Hugging Face model README
GGUF conversion of alwaysgood/qwen35_sft_023_dpo for llama.cpp and LM Studio.
| File | Purpose |
|---|---|
qwen35_sft_023_dpo-Q4_K_M.gguf | Main text model, recommended default |
qwen35_sft_023_dpo-mmproj-BF16.gguf | Multimodal projector for vision/image input |
qwen35_sft_023_dpo-BF16.gguf | BF16 text model, larger reference build |
The main BF16 and Q4_K_M GGUF files are language/text models. Vision/image tensors are split into the separate mmproj-BF16 GGUF, so image input requires loading both the main model and the matching mmproj file.
This model was trained with a raw DPO/SFT translation prompt, not a ChatML chat prompt. LM Studio's normal User/Assistant split can still be used by putting the fixed Instruction and Source headers in the custom template.
In LM Studio, open the model settings, go to Advanced Configuration -> Prompt Template, choose Custom, and use:
| Field | Value |
|---|---|
| Choose template | Custom |
| Before System | leave empty |
| After System | \n\n |
| Before User | ### Instruction:\nTranslate the English source into Korean.\n\n### Source:\n |
| After User | \n\n |
| Before Assistant | ### Response:\n |
| After Assistant | \n\n |
If you type this in LM Studio chat:
The Federal Reserve raised interest rates by 25 basis points.
LM Studio should send this prompt to the model:
### Instruction:
Translate the English source into Korean.
### Source:
The Federal Reserve raised interest rates by 25 basis points.
### Response:
Suggested decoding: greedy or low-temperature translation, e.g. temperature 0.0 to 0.3, context length 8192.
Text:
llama-cli \
-m qwen35_sft_023_dpo-Q4_K_M.gguf \
--color -ngl all -fa -c 8192 \
-p $'### Instruction:\nTranslate the English source into Korean.\n\n### Source:\nThe Federal Reserve raised interest rates by 25 basis points.\n\n### Response:\n'
Vision:
llama-mtmd-cli \
-m qwen35_sft_023_dpo-Q4_K_M.gguf \
--mmproj qwen35_sft_023_dpo-mmproj-BF16.gguf \
--image /path/to/image.png \
-p $'### Instruction:\nTranslate the English source into Korean.\n\n### Source:\nDescribe this image in Korean.\n\n### Response:\n' \
-ngl all -fa -c 8192
The source checkpoint contains both language and vision tensors. The GGUF text model was converted with the vision tensors split out, and the multimodal projector was converted separately.
Smoke test result with llama.cpp:
Q: 1+1=? A: 2