pmangesh
/

25M0831-Week10-Compression40-Submission01

8-bit precision

Model card Files Files and versions

25M0831-Week10-Compression40-Submission01

3.43 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

pmangesh's picture

Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B

ee949f7 verified 17 days ago

.gitattributes

1.57 kB
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
chat_template.jinja

7.76 kB
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
config.json

3.16 kB
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
merges.txt

3.35 MB
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
model.safetensors

3.41 GB
xet

Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
preprocessor_config.json

390 Bytes
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
quant_config.json

67.2 kB
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
tokenizer.json

12.8 MB
xet

Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
tokenizer_config.json

16.7 kB
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
video_preprocessor_config.json

385 Bytes
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago
vocab.json

6.72 MB
Compression_40: int8 embedding + 6-bit GPTQ (g128), 39.385% of Qwen3.5-4B 17 days ago