Downloads · 30 days
228
21% of all-time downloads
gemma4_1-0-8_sft_16bit_vllm
didula-wso2/gemma4_1-0-8_sft_16bit_vllm
gemma4_1-0-8_sft_16bit_vllm is a image-text-to-text model from didula-wso2. 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 transformers.
Ballerina SFT of unsloth/gemma-4-E4B-it: LoRA r16/alpha32 on all attention and MLP projections, one epoch over 9,182 samples (easy x2, klge x4, funcmain x4) with rules-free system prompts, lr 1e-4 cosine, seed 3407 (s…
All-time downloads
1.1K
Public
Parameters
8B
16 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- gemma4
- Access
- Public
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026
- SHA
- 82aa0c6c
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma4_1-0-8 (merged 16-bit)
Ballerina SFT of unsloth/gemma-4-E4B-it: LoRA r16/alpha32 on all attention and MLP projections,
one epoch over 9,182 samples (easy x2, klge x4, funcmain x4) with rules-free system prompts,
lr 1e-4 cosine, seed 3407 (sft_unified/configs/gemma4_1-0-8.yaml, checkpoint-574, 2026-09-16).
Adapter merged into the bf16 base on the language-model modules; vision/audio LoRA weights were
untrained zeros. Tokenizer and chat template are the base checkpoint's, untouched.
Ballerina HumanEval-style benchmark (rules-free funcmain prompt, t=0.8, top-p 0.95, seed 3407): 90/159. Python HumanEval pass@1 (3 samples, t=0.8): 94.3% (base: 94.9%).
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026