hoanglv7501
/

Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug

Image-Text-to-Text

text-generation-inference

4-bit precision

Model card Files Files and versions

Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug

2.47 GB

1 contributor

History: 5 commits

hoanglv7501's picture

Update tokenizer_config.json

84772c4 verified 3 months ago

.gitattributes

1.57 kB

Modifying tokenizer_config.json to fix EOS token 3 months ago
README.md

18.9 kB

Modifying tokenizer_config.json to fix EOS token 3 months ago
added_tokens.json

629 Bytes

Modifying tokenizer_config.json to fix EOS token 3 months ago
chat_template.jinja

1.02 kB

Modifying tokenizer_config.json to fix EOS token 3 months ago
chat_template.json

1.05 kB

Modifying tokenizer_config.json to fix EOS token 3 months ago
config.json

2.18 kB

Modifying tokenizer_config.json to fix EOS token 3 months ago
generation_config.json

251 Bytes

Modifying tokenizer_config.json to fix EOS token 3 months ago
merges.txt

1.82 MB

Modifying tokenizer_config.json to fix EOS token 3 months ago
model.safetensors

2.46 GB
xet

Modifying tokenizer_config.json to fix EOS token 3 months ago
preprocessor_config.json

604 Bytes

Modifying tokenizer_config.json to fix EOS token 3 months ago
special_tokens_map.json

645 Bytes

Modifying tokenizer_config.json to fix EOS token 3 months ago
tokenizer.json

11.4 MB
xet

Modifying tokenizer_config.json to fix EOS token 3 months ago
tokenizer_config.json

4.76 kB

Update tokenizer_config.json 3 months ago
vocab.json

2.78 MB

Modifying tokenizer_config.json to fix EOS token 3 months ago