TinyLamda commited on
Commit
0fe4a2e
·
verified ·
1 Parent(s): fee17ce

add w4a8_q3_14b readme

Browse files
Files changed (1) hide show
  1. w4a8_q3_14b/README.md +4 -0
w4a8_q3_14b/README.md ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # w4a8_q3_14b
2
+
3
+ Quantized Qwen3-14B checkpoints (qmodels/), 4-bit weight packs (packs/) and build caches (dc_cache/) from W4A8KV4 experiments, November 2026.
4
+ Derived from Qwen/Qwen3-14B (Apache-2.0); weights were modified by quantization.