OpenRAL/rskill-topreward_qwen3vl_4b-any-general-nf4 at main

rskill-topreward_qwen3vl_4b-any-general-nf4

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

AdrianLlopart's picture

docs: HF model card for OpenRAL/rskill-topreward_qwen3vl_4b-any-general-nf4 v0.1.0

d3a775c verified about 1 month ago

media
chore: publish rSkill OpenRAL/rskill-topreward-qwen3vl-4b-nf4 v0.1.0 2 months ago
.gitattributes

1.63 kB
Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago
README.md

7 kB
docs: HF model card for OpenRAL/rskill-topreward_qwen3vl_4b-any-general-nf4 v0.1.0 about 1 month ago
SKILL.md

3.59 kB
chore: canonical naming migration 2 months ago
chat_template.jinja

5.29 kB
Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago
config.json

2.06 kB
Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago
generation_config.json

241 Bytes
Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago
model.safetensors

2.87 GB
xet

Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago
processor_config.json

1.19 kB
Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago
rskill.yaml

4.17 kB
chore: canonical naming migration 2 months ago
tokenizer.json

11.4 MB
xet

Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago
tokenizer_config.json

706 Bytes
Add pre-quantized NF4 Qwen3-VL-4B weights (2.89 GB) — load 4-bit directly, no re-quantize 2 months ago