techwithsergiu
/

Qwen3.5-0.8B-bnb-4bit

Image-Text-to-Text

4-bit precision

Model card Files Files and versions

Qwen3.5-0.8B-bnb-4bit

998 MB

Ctrl+K

Ctrl+K

1 contributor

History: 15 commits

techwithsergiu's picture

docs: upd diagrams, new qwen-qlora-train, qwen35-toolkit links

313205c verified about 1 month ago

diagrams
docs: upd diagrams, new qwen-qlora-train, qwen35-toolkit links about 1 month ago
.gitattributes

1.69 kB
upd .gitattributes about 1 month ago
README.md

3.3 kB
docs: upd diagrams, new qwen-qlora-train, qwen35-toolkit links about 1 month ago
chat_template.jinja

7.82 kB
Upload a quantized BNB 4-bit model about 1 month ago
config.json

3.07 kB
Fixed quantization_config.llm_int8_skip_modules, to avoid re-quantizes embed_tokens layers on load about 1 month ago
generation_config.json

141 Bytes
Upload a quantized BNB 4-bit model about 1 month ago
merges.txt

3.35 MB
Add missing side-car files about 1 month ago
model.safetensors

968 MB
xet

Upload a quantized BNB 4-bit model about 1 month ago
preprocessor_config.json

336 Bytes
Add missing side-car files about 1 month ago
processor_config.json

1.3 kB
Add missing side-car files about 1 month ago
tokenizer.json

20 MB
xet

Upload a quantized BNB 4-bit model about 1 month ago
tokenizer_config.json

9.25 kB
Upload a quantized BNB 4-bit model about 1 month ago
video_preprocessor_config.json

385 Bytes
Add missing side-car files about 1 month ago
vocab.json

6.72 MB
Add missing side-car files about 1 month ago