PrunaAI
/

HuggingFaceTB-SmolLM2-135M-Instruct-HQQ-4bit-smashed

Model card Files Files and versions

HuggingFaceTB-SmolLM2-135M-Instruct-HQQ-4bit-smashed

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

begumcig's picture

Upload folder using huggingface_hub (#2)

9dc7a92 verified 6 months ago

.gitattributes

1.52 kB

initial commit 6 months ago
README.md

5.55 kB

Upload folder using huggingface_hub (#1) 6 months ago
base_results.json

877 Bytes

Upload folder using huggingface_hub (#2) 6 months ago
config.json

1.44 kB

Upload folder using huggingface_hub (#1) 6 months ago
merges.txt

466 kB

Upload folder using huggingface_hub (#1) 6 months ago
plots.png

552 kB

Upload folder using huggingface_hub (#2) 6 months ago
qmodel.pt
Detected Pickle imports (8)
- "torch.HalfStorage",
- "torch.uint8",
- "collections.OrderedDict",
- "torch.ByteStorage",
- "torch.Size",
- "torch.float16",
- "torch._utils._rebuild_tensor_v2",
- "torch._utils._rebuild_parameter"
How to fix it?
117 MB
xet

Upload folder using huggingface_hub (#1) 6 months ago
smash_config.json

1.11 kB

Upload folder using huggingface_hub (#1) 6 months ago
smashed_results.json

877 Bytes

Upload folder using huggingface_hub (#2) 6 months ago
special_tokens_map.json

655 Bytes

Upload folder using huggingface_hub (#1) 6 months ago
tokenizer.json

3.52 MB

Upload folder using huggingface_hub (#1) 6 months ago
tokenizer_config.json

3.76 kB

Upload folder using huggingface_hub (#1) 6 months ago
vocab.json

801 kB

Upload folder using huggingface_hub (#1) 6 months ago