inferencerlabs commited on
Commit
7fa1142
·
verified ·
1 Parent(s): 837971a

Upload complete model

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -6,11 +6,11 @@ tags:
6
  - mlx
7
  pipeline_tag: text-generation
8
  ---
9
- ## CURRENTLY UPLOADING FILES
10
  This notice will be removed once all files have been uploaded.
11
- ...
12
 
13
- **See DeepSeek-V3.1 5.5bit MLX in action - [demonstration video](https://youtube.com/xcreate)**
 
14
 
15
  *q5.5bit quant typically achieves 1.141 perplexity in our testing*
16
  | Quantization | Perplexity |
@@ -26,6 +26,6 @@ This notice will be removed once all files have been uploaded.
26
 
27
  * Runs on a single M3 Ultra 512GB RAM
28
  * Memory usage: ~480 GB
29
- * Expect ~15 tokens/s
30
  * Built with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.26
31
- * For more details see [demonstration video](https://youtube.com/xcreate) or visit [DeepSeek-V3.1](https://huggingface.co/deepseek-ai/DeepSeek-V3.1).
 
6
  - mlx
7
  pipeline_tag: text-generation
8
  ---
9
+ ## ----CURRENTLY UPLOADING FILES-----
10
  This notice will be removed once all files have been uploaded.
 
11
 
12
+ ## Notes
13
+ **See DeepSeek-V3.1 5.5bit MLX in action - [demonstration video](hhttps://youtu.be/ufXZI6aqOU8)**
14
 
15
  *q5.5bit quant typically achieves 1.141 perplexity in our testing*
16
  | Quantization | Perplexity |
 
26
 
27
  * Runs on a single M3 Ultra 512GB RAM
28
  * Memory usage: ~480 GB
29
+ * Expect ~13-19 tokens/s
30
  * Built with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.26
31
+ * For more details see [demonstration video](https://youtu.be/ufXZI6aqOU8) or visit [DeepSeek-V3.1](https://huggingface.co/deepseek-ai/DeepSeek-V3.1).