maxence-bouvier
/

Devstral-Small-2-24B-Instruct-SINQ-4bit

Text Generation

4-bit precision

8-bit precision

Model card Files Files and versions

Devstral-Small-2-24B-Instruct-SINQ-4bit

30.3 GB

1 contributor

History: 13 commits

maxence-bouvier's picture

maxence-bouvier

Update README.md

f402aa8 verified about 2 months ago

*.json
Re-quantize with ASINQ 4-bit about 2 months ago
.gitattributes
1.57 kB

Upload SINQ 4-bit quantized Devstral-Small-2-24B about 2 months ago
README.md
5.91 kB

Update README.md about 2 months ago
chat_template.jinja
5.32 kB

Upload SINQ 4-bit quantized Devstral-Small-2-24B about 2 months ago
config.json
1.69 kB

Fix tokenizer config and weight key prefixes about 2 months ago
model-00001-of-00004.safetensors
4.28 GB
xet

Fix tokenizer config and weight key prefixes about 2 months ago
model-00002-of-00004.safetensors
4.24 GB
xet

Fix tokenizer config and weight key prefixes about 2 months ago
model-00003-of-00004.safetensors
4.24 GB
xet

Fix tokenizer config and weight key prefixes about 2 months ago
model-00004-of-00004.safetensors
2.02 GB
xet

Fix tokenizer config and weight key prefixes about 2 months ago
model.safetensors.index.json
372 kB

Fix tokenizer config and weight key prefixes about 2 months ago
model.safetensors.index.json.meta.json
226 kB

Fix tokenizer config and weight key prefixes about 2 months ago
processor_config.json
976 Bytes

Upload SINQ 4-bit quantized Devstral-Small-2-24B about 2 months ago
special_tokens_map.json
96 Bytes

Fix tokenizer config and weight key prefixes about 2 months ago
tokenizer.json
17.1 MB
xet

Upload SINQ 4-bit quantized Devstral-Small-2-24B about 2 months ago
tokenizer_config.json
38.1 kB

Fix tokenizer config and weight key prefixes about 2 months ago