JuzeZhang commited on
Commit
a4c9ac6
·
verified ·
1 Parent(s): ee2e65e

README: version note — weights updated to stage-5 multi-task distill (2026-05-30)

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -26,6 +26,12 @@ It is the **speech/text backbone** of [ViBES](https://github.com/Juzezhang/ViBES
26
  speech-language-behavior model) — a lightweight, low-latency alternative to the GLM-4-Voice-9B base.
27
  The motion experts are released separately: [`ViBES-Face`](https://huggingface.co/JuzeZhang/ViBES-Face).
28
 
 
 
 
 
 
 
29
  ## Model
30
 
31
  - **Architecture:** same `ChatGLMForConditionalGeneration` family as the teacher, scaled down —
 
26
  speech-language-behavior model) — a lightweight, low-latency alternative to the GLM-4-Voice-9B base.
27
  The motion experts are released separately: [`ViBES-Face`](https://huggingface.co/JuzeZhang/ViBES-Face).
28
 
29
+ > **Version note (2026-05-30):** the weights were updated to our latest distillation checkpoint —
30
+ > the final **stage-5 multi-task** model of the distillation pipeline (covering the S2S / S2T / T2S /
31
+ > T2T modes below). Same architecture, tokenizer, and interface as the initial release; quality is
32
+ > improved. ViBES 0.5B motion experts trained against an earlier snapshot should be retrained or
33
+ > re-validated against this base.
34
+
35
  ## Model
36
 
37
  - **Architecture:** same `ChatGLMForConditionalGeneration` family as the teacher, scaled down —