Hugging Face's logo

mradermacher
/
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k-GGUF

Transformers
GGUF
English
Generated from Trainer
open-r1
trl
grpo
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
3549ea4
·
verified ·
1 Parent(s): cceb00c

uploaded from leia

Browse files
Files changed (13) hide show
  1. .gitattributes +12 -0
  2. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.IQ4_XS.gguf +3 -0
  3. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q2_K.gguf +3 -0
  4. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_L.gguf +3 -0
  5. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_M.gguf +3 -0
  6. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_S.gguf +3 -0
  7. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q4_K_M.gguf +3 -0
  8. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q4_K_S.gguf +3 -0
  9. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q5_K_M.gguf +3 -0
  10. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q5_K_S.gguf +3 -0
  11. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q6_K.gguf +3 -0
  12. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q8_0.gguf +3 -0
  13. Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.f16.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ 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
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.f16.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8735e1712aa81c3b5a5dd634ac31d3c027b78b965f0e650751fe05663abcf16
3
+ size 902183552
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f87de14209215f895281265599ef50436706660abac414fc73868bb5effbd24
3
+ size 676305536
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d10ac007c623e9b09b908eb1d5f3b54f1da5004158d202cfa786b755c2ae5b
3
+ size 880163456
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154913b7b074e809a460e916da8a098c763cb6f3d8f0a4c26dc7199c538ded72
3
+ size 824179328
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ae2c53f02ef3bef3297c933d5c292cac1654e3097d476e51b35d766af42ceb
3
+ size 760945280
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:159d9ce78b2362250bd9355a4dbd76e129242ccd8d154bc86b73260d0cb9142b
3
+ size 986049152
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cab041c4392ffc0b91b9c76b1a2061a549968b9ac99d10dc5d0db4ca4d4572e
3
+ size 940313216
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e41832935bc4c03b50e8f7dda3ca1f4caf68e9573373fa293b87a50fa111f73
3
+ size 1125051008
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c87ef04ef4ac1ec86b6a55196660f0479b5ef70f07db23f17a53647cde74b62
3
+ size 1098730112
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa4d6144f70439ab619aa4f073f68bb123ea8d168f5bd15319289a1754c632e
3
+ size 1272740480
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b829f9aaad27ac9d910ef05126e9a7c8e866675c4a7e62a1a61171465fc03dd5
3
+ size 1646573696
Qwen2.5-1.5B-Code-GRPO-dense-reward-3k.f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74f3c36a305c211086aa2a9a0fc6530a82db39891508f6b59234ed435d3e947
3
+ size 3093670016