danielhanchen commited on
Commit
bacf989
·
verified ·
1 Parent(s): bc200eb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -32,6 +32,7 @@ library_name: transformers
32
  <h1 style="margin-top:0rem; margin-bottom: 0rem;">🐋 DeepSeek-R1-0528-Qwen3-8B Usage Guidelines</h1>
33
  </div>
34
 
 
35
  - Set the temperature between **0.5–0.7 (0.6 recommended)** to reduce repetition and incoherence.
36
  - Set Top_P value of **0.95 (recommended)**
37
  - R1-0528 uses the same chat template as the original R1 model:
 
32
  <h1 style="margin-top:0rem; margin-bottom: 0rem;">🐋 DeepSeek-R1-0528-Qwen3-8B Usage Guidelines</h1>
33
  </div>
34
 
35
+ - For Ollama do `ollama run hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_XL` - it'll auto get the correct chat template and all settings
36
  - Set the temperature between **0.5–0.7 (0.6 recommended)** to reduce repetition and incoherence.
37
  - Set Top_P value of **0.95 (recommended)**
38
  - R1-0528 uses the same chat template as the original R1 model: