2.04 GB

Ctrl+K

1 contributor

8514c48 verified about 2 months ago

.gitattributes

1.57 kB
SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
added_tokens.json

35 Bytes
SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
chat_template.jinja

1.53 kB
SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
config.json

1.62 kB
SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
generation_config.json

174 Bytes
SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
model.safetensors

2 GB
xet

SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
special_tokens_map.json

662 Bytes
SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
tokenizer.json

33.4 MB
xet

SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
tokenizer.model

4.69 MB
xet

SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago
tokenizer_config.json

1.16 MB
SFT v7.0: VAZHI Tamil assistant | base=google/gemma-3-1b-it (Gemma 3 1B-it) | LoRA r=8 x ['q_proj', 'v_proj'] | lr=1e-05 | 3378 samples | Tamil word: 95% -> 94% about 2 months ago