Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
DiscoLM-70B-GGUF
like
3
Text Generation
Transformers
GGUF
9 datasets
English
German
llama
goliath
deutsch
llama2
discoresearch
License:
llama2
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
66308f4
DiscoLM-70B-GGUF
1 contributor
History:
13 commits
TheBloke
Upload in splits of max 50GB due to HF 50GB limit. (made with llama.cpp commit fbbc428)
66308f4
11 months ago
.gitattributes
2.38 kB
Upload in splits of max 50GB due to HF 50GB limit. (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q2_K.gguf
29.3 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q3_K_L.gguf
36.1 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q3_K_M.gguf
33.2 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q3_K_S.gguf
29.9 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q4_0.gguf
38.9 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q4_K_M.gguf
41.4 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q4_K_S.gguf
39.1 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q5_0.gguf
47.5 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q5_K_M.gguf
48.8 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q5_K_S.gguf
47.5 GB
LFS
GGUF model commit (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q6_K.gguf-split-a
28.3 GB
LFS
Upload in splits of max 50GB due to HF 50GB limit. (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q6_K.gguf-split-b
28.3 GB
LFS
Upload in splits of max 50GB due to HF 50GB limit. (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q8_0.gguf-split-a
36.6 GB
LFS
Upload in splits of max 50GB due to HF 50GB limit. (made with llama.cpp commit fbbc428)
11 months ago
discolm-70b.Q8_0.gguf-split-b
36.6 GB
LFS
Upload in splits of max 50GB due to HF 50GB limit. (made with llama.cpp commit fbbc428)
11 months ago