Hugging Face's logo

kenpath
/
bharat-pii-gemma-3-270m-it-gguf

GGUF
conversational
Model card Files
xet
Community
adityachhabra commited on
Commit
f0e2067
·
verified ·
1 Parent(s): d6e103f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -1,8 +1,8 @@
1
- ## Bharat PII Gemma 3 1B (GGUF)
2
 
3
  Files
4
- - bharat-pii-gemma-3-1b-it-v0.3-f16.gguf
5
- - bharat-pii-gemma-3-1b-it-v0.3_q8_0.gguf
6
 
7
  Notes
8
  - GGUF is self-contained (includes tokenizer/config metadata).
@@ -10,4 +10,4 @@ Notes
10
  - Suggested: q8_0 for general use, f16 for reference/evaluation.
11
 
12
  Example (llama.cpp)
13
- - ./main -m ./bharat-pii-gemma-3-1b-it-v0.3-q8_0.gguf -p "Hello"
 
1
+ ## Bharat PII Gemma 3 270M (GGUF)
2
 
3
  Files
4
+ - bharat-pii-gemma-3-270m-it-v0.7-f16.gguf
5
+ - bharat-pii-gemma-3-270m-it-v0.7_q8_0.gguf
6
 
7
  Notes
8
  - GGUF is self-contained (includes tokenizer/config metadata).
 
10
  - Suggested: q8_0 for general use, f16 for reference/evaluation.
11
 
12
  Example (llama.cpp)
13
+ - ./main -m ./bharat-pii-gemma-3-270m-it-v0.7_q8_0.gguf -p "My name is ..."