PrunaAI
/

AI-Sweden-Models-Llama-3-8B-HQQ-4bit-smashed

Text Generation

Inference Endpoints

Model card Files Files and versions Community

AI-Sweden-Models-Llama-3-8B-HQQ-4bit-smashed

1 contributor

History: 4 commits

sharpenb's picture

27f32d7a9575049db4df1fb15691f6a69b1516406b3b08f0d8d22b64dad804f9

36d3f80 verified 4 months ago

.gitattributes

1.52 kB

initial commit 5 months ago
README.md

5.31 kB

27f32d7a9575049db4df1fb15691f6a69b1516406b3b08f0d8d22b64dad804f9 4 months ago
config.json

688 Bytes

Upload folder using huggingface_hub (#1) 5 months ago
qmodel.pt
Detected Pickle imports (8)
- "torch.uint8",
- "torch._utils._rebuild_tensor_v2",
- "torch.Size",
- "torch.float16",
- "torch.ByteStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_parameter",
- "torch.HalfStorage"
How to fix it?
5.76 GB
LFS

Upload folder using huggingface_hub (#1) 5 months ago
results.json

754 Bytes

27f32d7a9575049db4df1fb15691f6a69b1516406b3b08f0d8d22b64dad804f9 4 months ago
smash_config.json

1.02 kB

Upload folder using huggingface_hub (#1) 5 months ago
special_tokens_map.json

449 Bytes

Upload folder using huggingface_hub (#1) 5 months ago
tokenizer.json

9.09 MB

Upload folder using huggingface_hub (#1) 5 months ago
tokenizer_config.json

50.6 kB

Upload folder using huggingface_hub (#1) 5 months ago