Hugging Face's logo

nisten
/
qwenv2-7b-inst-imatrix-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
nisten commited on
Commit
49deabb
•
1 Parent(s): 081ce53

Upload 9 files

Browse files

All my experiments that produced good results

Files changed (10) hide show
  1. .gitattributes +9 -0
  2. qwen7bf16.gguf +3 -0
  3. qwen7bq4kembeddingbf16outputbf16.gguf +3 -0
  4. qwen7bq4koutput8bit.gguf +3 -0
  5. qwen7bq4xs.gguf +3 -0
  6. qwen7bq4xsembedding5bitkoutput8bit.gguf +3 -0
  7. qwen7bq4xsoutput8bit.gguf +3 -0
  8. qwen7bq5km.gguf +3 -0
  9. qwenq8bitimatrix.dat +3 -0
  10. qwenq8v2.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,12 @@ 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
+ qwen7bf16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ qwen7bq4kembeddingbf16outputbf16.gguf filter=lfs diff=lfs merge=lfs -text
38
+ qwen7bq4koutput8bit.gguf filter=lfs diff=lfs merge=lfs -text
39
+ qwen7bq4xs.gguf filter=lfs diff=lfs merge=lfs -text
40
+ qwen7bq4xsembedding5bitkoutput8bit.gguf filter=lfs diff=lfs merge=lfs -text
41
+ qwen7bq4xsoutput8bit.gguf filter=lfs diff=lfs merge=lfs -text
42
+ qwen7bq5km.gguf filter=lfs diff=lfs merge=lfs -text
43
+ qwenq8bitimatrix.dat filter=lfs diff=lfs merge=lfs -text
44
+ qwenq8v2.gguf filter=lfs diff=lfs merge=lfs -text
qwen7bf16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfd06d4f9911b033ef0574937de75878e4d7719bd89966203162a31b1a39f6f
3
+ size 15237850656
qwen7bq4kembeddingbf16outputbf16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f0117f8970e9eb4c040296b773268db4c72827ea5546a6a146c48e56a3a1ea
3
+ size 6109431552
qwen7bq4koutput8bit.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2963991d78d1937c31a580539e3bf541e06f1ab6d198c5172997a176381155
3
+ size 4815062784
qwen7bq4xs.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3b2365e61a7834e8403516954a6665363c66ce0f4db8af7b4e77bb9a37c00a
3
+ size 4218470144
qwen7bq4xsembedding5bitkoutput8bit.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23da1e0d3619ea20ebc77ec0627fe278e9164b255bf98a6d9fae713475c29ad
3
+ size 4639991552
qwen7bq4xsoutput8bit.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6722c2295e8d4bdea93990f2ef3f746366fad81631dcb5ab52759d8525a504
3
+ size 4350461696
qwen7bq5km.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50c9226270edee91afbb988f84bbe0456a7e78bdfdfb6127af1ae22cca3bf15
3
+ size 5576820480
qwenq8bitimatrix.dat ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690c315c1cac97e20ce87473b9c98df2b6c4c26f60c0a1d9564b63aeb4f33003
3
+ size 4536673
qwenq8v2.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b4385ad242aa8276e9ec865c6500552fb5d5fa80b62dd77eee4ce8eb7e9a20
3
+ size 8098522656