TheBloke
/

Iambe-Storyteller-20B-GGUF

Model card Files Files and versions

Iambe-Storyteller-20B-GGUF

151 GB

1 contributor

History: 15 commits

TheBloke's picture

GGUF model commit (made with llama.cpp commit fe680e3)

d79c62d almost 2 years ago

.gitattributes

2.35 kB

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
LICENSE.txt

7.02 kB

Add Llama 2 license files almost 2 years ago
Notice

112 Bytes

Add Llama 2 license files almost 2 years ago
USE_POLICY.md

4.77 kB

Add Llama 2 license files almost 2 years ago
config.json

29 Bytes

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q2_K.gguf

8.31 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q3_K_L.gguf

10.6 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q3_K_M.gguf

9.7 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q3_K_S.gguf

8.66 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q4_0.gguf

11.3 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q4_K_M.gguf

12 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q4_K_S.gguf

11.3 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q5_0.gguf

13.8 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q5_K_M.gguf

14.2 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q5_K_S.gguf

13.8 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q6_K.gguf

16.4 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago
iambe-storyteller-20b.Q8_0.gguf

21.2 GB
xet

GGUF model commit (made with llama.cpp commit fe680e3) almost 2 years ago