Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
TheBloke
/
zephyr-7B-beta-GGUF
like
226
Transformers
GGUF
HuggingFaceH4/ultrachat_200k
HuggingFaceH4/ultrafeedback_binarized
English
mistral
Generated from Trainer
arxiv:
2305.18290
arxiv:
2310.16944
License:
mit
Model card
Files
Files and versions
Community
13
Train
Deploy
Use this model
main
zephyr-7B-beta-GGUF
1 contributor
History:
16 commits
TheBloke
Upload README.md
e4714d1
about 1 year ago
.gitattributes
Safe
2.27 kB
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
README.md
Safe
35.9 kB
Upload README.md
about 1 year ago
config.json
Safe
31 Bytes
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q2_K.gguf
Safe
3.08 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q3_K_L.gguf
Safe
3.82 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q3_K_M.gguf
Safe
3.52 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q3_K_S.gguf
Safe
3.16 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q4_0.gguf
Safe
4.11 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q4_K_M.gguf
Safe
4.37 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q4_K_S.gguf
Safe
4.14 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q5_0.gguf
Safe
5 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q5_K_M.gguf
Safe
5.13 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q5_K_S.gguf
Safe
5 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q6_K.gguf
Safe
5.94 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago
zephyr-7b-beta.Q8_0.gguf
Safe
7.7 GB
LFS
GGUF model commit (made with llama.cpp commit 34b2a5e)
about 1 year ago