nisten commited on
Commit
1c08e29
1 Parent(s): 6ca9816

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -27,8 +27,6 @@ aria2c -x 9 -o deepseek_0628_cpu_optimized_iq4xm-00004-of-00004.gguf \
27
  https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek_0628_cpu_optimized_iq4xm-00004-of-00004.gguf
28
  ```
29
 
30
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/rbdug3j6BaeTSmKLDIp39.png)
31
-
32
  ### 🧠 This IQ4XM version uses GGML TYPE IQ_4_XS 4bit in combination with q8_0 bit for blazing fast performance with minimal loss, leveraging int8 optimizations on most newer server CPUs.
33
  ### 🛠️ While it required some custom code wizardry, it's fully compatible with standard llama.cpp from GitHub or just search for nisten in lmstudio.
34
 
@@ -140,7 +138,7 @@ DeepSeek-V2-Chat-0628 is the latest and greatest in the DeepSeek family. This AI
140
  - 🏆 Overall Arena Ranking: #11 global
141
  - 💻 Coding Arena Ranking: #3, global
142
  - 🧠 Hard Prompts Arena Ranking: #7 global, better than claude opus even in english only hard-prompts
143
-
144
  Want to seek deeper into this model's ocean of awesomeness? Swim over to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat-0628) and prepare to have your mind blown! 🤯
145
 
146
  Now go forth and accelerate 🚀💡
 
27
  https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek_0628_cpu_optimized_iq4xm-00004-of-00004.gguf
28
  ```
29
 
 
 
30
  ### 🧠 This IQ4XM version uses GGML TYPE IQ_4_XS 4bit in combination with q8_0 bit for blazing fast performance with minimal loss, leveraging int8 optimizations on most newer server CPUs.
31
  ### 🛠️ While it required some custom code wizardry, it's fully compatible with standard llama.cpp from GitHub or just search for nisten in lmstudio.
32
 
 
138
  - 🏆 Overall Arena Ranking: #11 global
139
  - 💻 Coding Arena Ranking: #3, global
140
  - 🧠 Hard Prompts Arena Ranking: #7 global, better than claude opus even in english only hard-prompts
141
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/rbdug3j6BaeTSmKLDIp39.png)
142
  Want to seek deeper into this model's ocean of awesomeness? Swim over to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat-0628) and prepare to have your mind blown! 🤯
143
 
144
  Now go forth and accelerate 🚀💡