Hugging Face's logo

ZeroWw
/
QwQ-LCoT-3B-Instruct-GGUF

Text Generation
GGUF
English
Inference Endpoints
conversational
Model card Files Community
ZeroWw commited on
Commit
0e860d7
·
verified ·
1 Parent(s): ca1ef82

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +6 -0
  2. QwQ-LCoT-3B-Instruct.f16.gguf +3 -0
  3. QwQ-LCoT-3B-Instruct.q5_k.gguf +3 -0
  4. QwQ-LCoT-3B-Instruct.q6_k.gguf +3 -0
  5. QwQ-LCoT-3B-Instruct.q8_0.gguf +3 -0
  6. QwQ-LCoT-3B-Instruct.q8_p.gguf +3 -0
  7. QwQ-LCoT-3B-Instruct.q8q4.gguf +3 -0
  8. README.md +17 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ QwQ-LCoT-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ QwQ-LCoT-3B-Instruct.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
38
+ QwQ-LCoT-3B-Instruct.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
39
+ QwQ-LCoT-3B-Instruct.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
+ QwQ-LCoT-3B-Instruct.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
41
+ QwQ-LCoT-3B-Instruct.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
QwQ-LCoT-3B-Instruct.f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c59700cefb9bcd3c531985d7aae04c55ae6a24c9127e11bbd84bbac70e04024
3
+ size 6178317504
QwQ-LCoT-3B-Instruct.q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297dc0345cb1fa93a625ad8dee719d23ab3a1087cf894bad66441b43861f6fc2
3
+ size 2591892672
QwQ-LCoT-3B-Instruct.q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fad04bb4fe0568ba2380665e0af6b5a38e84105241216651f82b76f10069e8b
3
+ size 2905236672
QwQ-LCoT-3B-Instruct.q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35cca92169fcaa0b318ee4fe48c3bf62795f87a2e8c28e45d45973cddbbd77bc
3
+ size 3577193664
QwQ-LCoT-3B-Instruct.q8_p.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5936addb2df27071a8eb7e76abed6415a3f95e3eeb5f5c3c6cac238db5c14d9
3
+ size 3285476544
QwQ-LCoT-3B-Instruct.q8q4.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1020ca3d41f694b4b21f62558605ee9ef8175a0bb334523f579bc7610f554d43
3
+ size 2005263552
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: mit
4
+ language:
5
+ - en
6
+ pipeline_tag: text-generation
7
+ ---
8
+
9
+ My own (ZeroWw) quantizations.
10
+ output and embed tensors quantized to f16.
11
+ all other tensors quantized to q5_k or q6_k.
12
+
13
+ Result:
14
+ both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
15
+ and they perform as well as the pure f16.
16
+
17
+ Updated on: Thu Jan 16, 16:22:00