Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ErikFeng
/
DeepSeek-R1-Distill-Llama-70B-Science-Q4_K_M-GGUF
like
2
Text Generation
GGUF
meta-math/MetaMathQA
English
llama.cpp
quantization
q4_k_m
deepseek-r1
reasoning
mathematics
MetaMathQA
importance-matrix
imatrix
a100
conversational
arxiv:
2309.12284
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
DeepSeek-R1-Distill-Llama-70B-Science-Q4_K_M-GGUF
42.5 GB
1 contributor
History:
8 commits
ErikFeng
Update README.md
edf49b9
verified
6 days ago
results
Restructered files
6 days ago
.gitattributes
Safe
1.6 kB
added model
6 days ago
DeepSeek-R1-Distill-Llama-70B-Q4_K_M-science.gguf
Safe
42.5 GB
xet
added model
6 days ago
README.md
Safe
11.8 kB
Update README.md
6 days ago
eval_science.txt
Safe
64.2 kB
Add science-calibrated Q4_K_M GGUF and calibration artifacts
6 days ago
imatrix_science.dat
24.9 MB
xet
Add science-calibrated Q4_K_M GGUF and calibration artifacts
6 days ago
science_calibration.txt
Safe
1.49 MB
Add science-calibrated Q4_K_M GGUF and calibration artifacts
6 days ago
