Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
celestialcreator
/
Llama-3.2-1B-MTP-k8
like
1
Text Generation
Transformers
PyTorch
jwkirchenbauer/metamathqa-grouped-split
English
llama
multi-token-prediction
speculative-decoding
self-distillation
mtp
consumer-gpu
rtx-5090
paper-reproduction
custom_code
Eval Results (legacy)
text-generation-inference
arxiv:
2602.06019
License:
llama3.2
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Llama-3.2-1B-MTP-k8
3.42 GB
1 contributor
History:
11 commits
celestialcreator
Update README.md
687979a
verified
4 days ago
.gitattributes
Safe
1.57 kB
Upload tokenizer.json with huggingface_hub
4 days ago
README.md
6.76 kB
Update README.md
4 days ago
config.json
1.02 kB
Upload config.json with huggingface_hub
4 days ago
configuration_llama.py
Safe
12.1 kB
Upload configuration_llama.py with huggingface_hub
4 days ago
generation_config.json
Safe
230 Bytes
Upload generation_config.json with huggingface_hub
4 days ago
modeling_llama.py
40.7 kB
Upload modeling_llama.py with huggingface_hub
4 days ago
pytorch_model.bin
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
What is a pickle import?
3.4 GB
xet
Upload pytorch_model.bin with huggingface_hub
4 days ago
special_tokens_map.json
5.54 kB
Upload special_tokens_map.json with huggingface_hub
4 days ago
tokenizer.json
17.2 MB
xet
Upload tokenizer.json with huggingface_hub
4 days ago
tokenizer_config.json
57.8 kB
Upload tokenizer_config.json with huggingface_hub
4 days ago
