Hugging Face's logo

bbearforever
/
quantum-Qwen2.5-4-bit

Text Generation
English
quantum
oklo-reactor
quantization
4-bit precision
tq4_1s
mv2-format
conversational
Model card Files
xet
 Community
bbearforever commited on
Commit
eaa2460
·
verified ·
1 Parent(s): ad88bed

Update to latest .m31 format

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. Qwen2.5B-quantum-4bit.m31 +3 -0
.gitattributes CHANGED
@@ -157,3 +157,4 @@ tensor_data/model_layers_9_self_attn_q_proj_weight.quant filter=lfs diff=lfs mer
157
  Qwen2.5B-quantum-4bit.mv2 filter=lfs diff=lfs merge=lfs -text
158
  Qwen2.5B-quantum-4bit-v3.1.mv2 filter=lfs diff=lfs merge=lfs -text
159
  examples/skill-capsule.mv2 filter=lfs diff=lfs merge=lfs -text
 
 
157
  Qwen2.5B-quantum-4bit.mv2 filter=lfs diff=lfs merge=lfs -text
158
  Qwen2.5B-quantum-4bit-v3.1.mv2 filter=lfs diff=lfs merge=lfs -text
159
  examples/skill-capsule.mv2 filter=lfs diff=lfs merge=lfs -text
160
+ Qwen2.5B-quantum-4bit.m31 filter=lfs diff=lfs merge=lfs -text
Qwen2.5B-quantum-4bit.m31 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f0dbefb5ed63d2f3913f53e530b686ef011520561e3f787ccaec5f037c1732
3
+ size 192140217