Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Llama-2-70B-GGUF
like
29
Text Generation
Transformers
GGUF
PyTorch
English
llama
facebook
meta
llama-2
text-generation-inference
arxiv:
2307.09288
License:
llama2
Model card
Files
Files and versions
Community
4
Train
Deploy
Use this model
18dfb7a
Llama-2-70B-GGUF
1 contributor
History:
14 commits
TheBloke
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
18dfb7a
about 1 year ago
.gitattributes
2.38 kB
Upload in 50GiB chunks due to HF 50 GiB limit. (model made with llama.cpp commit 2ba85c8)
about 1 year ago
config.json
29 Bytes
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q2_K.gguf
29.3 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q3_K_L.gguf
36.1 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q3_K_M.gguf
33.2 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q3_K_S.gguf
29.9 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q4_0.gguf
38.9 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q4_K_M.gguf
41.4 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q4_K_S.gguf
39.1 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q5_0.gguf
47.5 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q5_K_M.gguf
48.8 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q5_K_S.gguf
47.5 GB
LFS
Initial GGUF model commit (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q6_K.gguf-split-a
36.7 GB
LFS
Upload in 50GiB chunks due to HF 50 GiB limit. (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q6_K.gguf-split-b
19.9 GB
LFS
Upload in 50GiB chunks due to HF 50 GiB limit. (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q8_0.gguf-split-a
36.7 GB
LFS
Upload in 50GiB chunks due to HF 50 GiB limit. (model made with llama.cpp commit 2ba85c8)
about 1 year ago
llama-2-70b.Q8_0.gguf-split-b
36.6 GB
LFS
Upload in 50GiB chunks due to HF 50 GiB limit. (model made with llama.cpp commit 2ba85c8)
about 1 year ago