TheBloke
/

Huginn-22B-Prototype-GGUF

Model card Files Files and versions

Huginn-22B-Prototype-GGUF

165 GB

1 contributor

History: 33 commits

TheBloke's picture

Update base_model formatting

161592c over 2 years ago

.gitattributes
2.34 kB

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
LICENSE.txt
7.02 kB

Add Llama 2 license files over 2 years ago
Notice
112 Bytes

Add Llama 2 license files over 2 years ago
README.md
15.3 kB

Update base_model formatting over 2 years ago
USE_POLICY.md
4.77 kB

Add Llama 2 license files over 2 years ago
config.json
29 Bytes

Initial GGUF model commit over 2 years ago
huginn-22b-prototype.Q2_K.gguf
9.08 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q3_K_L.gguf
11.6 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q3_K_M.gguf
10.6 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q3_K_S.gguf
9.47 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q4_0.gguf
12.3 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q4_K_M.gguf
13.2 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q4_K_S.gguf
12.4 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q5_0.gguf
15 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q5_K_M.gguf
15.5 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q5_K_S.gguf
15 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q6_K.gguf
17.9 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago
huginn-22b-prototype.Q8_0.gguf
23.2 GB
xet

Initial GGUF model commit (model made with llama.cpp commit d59bd97) over 2 years ago