SahilRS commited on
Commit
bc12667
·
verified ·
1 Parent(s): 0ac2f9d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -6,11 +6,11 @@ colorTo: purple
6
  sdk: gradio
7
  sdk_version: 5.9.1
8
  python_version: 3.11
9
- app_file: app_phase5a.py
10
  pinned: false
11
  ---
12
 
13
- # Phi-3 Mini Chatbot - Phase 5a
14
 
15
- Microsoft's Phi-3 Mini model with explicit FlashAttention 2.
16
- Current Phase: Phase 5a - FlashAttention 2 (flash-attn package)
 
6
  sdk: gradio
7
  sdk_version: 5.9.1
8
  python_version: 3.11
9
+ app_file: app_phase5b.py
10
  pinned: false
11
  ---
12
 
13
+ # Phi-3 Mini Chatbot - Phase 5b
14
 
15
+ Microsoft's Phi-3 Mini model with SDPA + Greedy decoding + Static KV cache.
16
+ Current Phase: Phase 5b - Greedy + Static KV Cache (do_sample=False, cache_implementation=static)