Text Generation
MLX
Safetensors
qwen3_moe
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
Qwen3-Coder-30B-A3B-Instruct
Qwen3-30B-A3B
mixture of experts
128 experts
8 active experts
1 million context
qwen3
finetune
brainstorm 20x
brainstorm
optional thinking
unsloth
conversational
6-bit
Update README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ pipeline_tag: text-generation
|
|
| 42 |
|
| 43 |
This is a new-old-stock version of the model, with embeddings at 6 bit.
|
| 44 |
|
| 45 |
-
The original
|
| 46 |
|
| 47 |
```bash
|
| 48 |
Perplexity: 4.455 ± 0.031
|
|
|
|
| 42 |
|
| 43 |
This is a new-old-stock version of the model, with embeddings at 6 bit.
|
| 44 |
|
| 45 |
+
The original Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx64-hi-mlx was using 4 bit embeddings, and was recently removed.
|
| 46 |
|
| 47 |
```bash
|
| 48 |
Perplexity: 4.455 ± 0.031
|