1.34 GB

Ctrl+K

1 contributor

Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute)

fbd7c09 verified 12 months ago

.gitattributes

1.57 kB
Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago
added_tokens.json

35 Bytes
Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago
config.json

2.02 kB
Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago
model.safetensors

1.3 GB
xet

Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago
special_tokens_map.json

670 Bytes
Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago
tokenizer.json

33.4 MB
xet

Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago
tokenizer.model

4.69 MB
xet

Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago
tokenizer_config.json

1.16 MB
Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute) 12 months ago