Hugging Face's logo

LWDCLS
/
Llama-3-8B-Stroganoff-GGUF-IQ-Imatrix-Request

GGUF
Inference Endpoints
imatrix
conversational
Model card Files Community
Lewdiculous commited on
Commit
0de2da3
•
1 Parent(s): c489261

Upload 9 files

Browse files
Files changed (10) hide show
  1. .gitattributes +8 -0
  2. Llama-3-8B-Stroganoff-BF16.gguf +3 -0
  3. Llama-3-8B-Stroganoff-F16.gguf +3 -0
  4. Llama-3-8B-Stroganoff-IQ3_M-imat.gguf +3 -0
  5. Llama-3-8B-Stroganoff-IQ3_XXS-imat.gguf +3 -0
  6. Llama-3-8B-Stroganoff-IQ4_XS-imat.gguf +3 -0
  7. Llama-3-8B-Stroganoff-Q4_K_M-imat.gguf +3 -0
  8. Llama-3-8B-Stroganoff-Q4_K_S-imat.gguf +3 -0
  9. imatrix-with-rp-ex.txt +0 -0
  10. imatrix.dat +3 -0
.gitattributes CHANGED
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ imatrix.dat filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3-8B-Stroganoff-BF16.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3-8B-Stroganoff-F16.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3-8B-Stroganoff-IQ3_M-imat.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-3-8B-Stroganoff-IQ3_XXS-imat.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-3-8B-Stroganoff-IQ4_XS-imat.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-3-8B-Stroganoff-Q4_K_M-imat.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama-3-8B-Stroganoff-Q4_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3-8B-Stroganoff-BF16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbd488142bdef6e25dcb7b56f53ef9f5b02579d282cdbfaae0b5a38c267ff26
3
+ size 16068890944
Llama-3-8B-Stroganoff-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4df7ceeb2a1b14307462f0cde174f9ba9e811e1c595f83316bf0e0bc5716000
3
+ size 16068890944
Llama-3-8B-Stroganoff-IQ3_M-imat.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6080ca7f2377983c274e309d22561d9b14fb53052ab565470b91f7e45de0b026
3
+ size 3784823392
Llama-3-8B-Stroganoff-IQ3_XXS-imat.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd02068cf3a0b4c09ae8a2a50f6641ae44a4779bc8af84ceb56b7f6e54d9f0d8
3
+ size 3274912352
Llama-3-8B-Stroganoff-IQ4_XS-imat.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f778a590c010ddcb126e94b95e16a747b127413d06b071c7595ed5bda905ed21
3
+ size 4447662688
Llama-3-8B-Stroganoff-Q4_K_M-imat.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f82c5456c68c9fcd958f7979e81814c1ec05439e50626af2961478392800de
3
+ size 4920734304
Llama-3-8B-Stroganoff-Q4_K_S-imat.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed710813c5b70574d26990195c25124117282ae4c45fcb78d78dd5d4fcd89e3
3
+ size 4692669024
imatrix-with-rp-ex.txt ADDED
The diff for this file is too large to render. See raw diff
 
imatrix.dat ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08fdc8018a9b7d0b80aba154155b2a01e9a1be06ff11cdf4342e6c428b89099
3
+ size 4988171