metascroy
/

Qwen3-4B-INT8-INT4

Text Generation

text-generation-inference

Model card Files Files and versions

Qwen3-4B-INT8-INT4

4.81 GB

1 contributor

History: 5 commits

metascroy's picture

Upload model trained with Unsloth

41a9095 verified about 2 months ago

.gitattributes

1.57 kB

Upload tokenizer about 2 months ago
README.md

5.19 kB

Upload model trained with Unsloth about 2 months ago
added_tokens.json

707 Bytes

Upload tokenizer about 2 months ago
chat_template.jinja

4.72 kB

Upload model trained with Unsloth about 2 months ago
config.json

2.91 kB

Upload model trained with Unsloth about 2 months ago
generation_config.json

237 Bytes

Upload model trained with Unsloth about 2 months ago
merges.txt

1.67 MB

Upload tokenizer about 2 months ago
pytorch_model.bin
Detected Pickle imports (12)
- "torch._tensor._rebuild_from_type_v2",
- "torch.CharStorage",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_wrapper_subclass",
- "torch._utils._rebuild_tensor_v2",
- "torch.int8",
- "collections.OrderedDict",
- "torchao.quantization.IntxUnpackedToInt8Tensor",
- "torch.int4",
- "torch.serialization._get_layout",
- "torch.bfloat16",
- "torch.device"
How to fix it?
4.79 GB
xet

Upload model trained with Unsloth about 2 months ago
special_tokens_map.json

614 Bytes

Upload model trained with Unsloth about 2 months ago
tokenizer.json

11.4 MB
xet

Upload tokenizer about 2 months ago
tokenizer_config.json

5.43 kB

Upload model trained with Unsloth about 2 months ago
vocab.json

2.78 MB

Upload tokenizer about 2 months ago