cs-552-2026-MandMP
/

multilingual_model

Model card Files Files and versions

multilingual_model

3.46 GB

Ctrl+K

Ctrl+K

1 contributor

History: 17 commits

eliorrr's picture

v10: bump README to retrigger CI eval

5c8c77e verified 5 months ago

.gitattributes

1.57 kB
v0: Qwen3-1.7B base + chat_template thinking OFF + system prompt boxed + gen_config tuned 6 months ago
LICENSE

11.3 kB
v0: Qwen3-1.7B base + chat_template thinking OFF + system prompt boxed + gen_config tuned 6 months ago
README.md

64 Bytes
v10: bump README to retrigger CI eval 5 months ago
chat_template.jinja

4.47 kB
v1: SFT LoRA on Global-MMLU 5 langs (it/es/zh/ru/hi), 13.5k samples, 1 epoch, fp16 merged 6 months ago
config.json

1.42 kB
v1: SFT LoRA on Global-MMLU 5 langs (it/es/zh/ru/hi), 13.5k samples, 1 epoch, fp16 merged 6 months ago
generation_config.json

242 Bytes
v0: Qwen3-1.7B base + chat_template thinking OFF + system prompt boxed + gen_config tuned 6 months ago
merges.txt

1.67 MB
v0: Qwen3-1.7B base + chat_template thinking OFF + system prompt boxed + gen_config tuned 6 months ago
model.safetensors

3.44 GB
xet

v10: SFT + Belebele + DPO 100% hard negatives 5 months ago
tokenizer.json

11.4 MB
xet

v1: SFT LoRA on Global-MMLU 5 langs (it/es/zh/ru/hi), 13.5k samples, 1 epoch, fp16 merged 6 months ago
tokenizer_config.json

693 Bytes
v1: SFT LoRA on Global-MMLU 5 langs (it/es/zh/ru/hi), 13.5k samples, 1 epoch, fp16 merged 6 months ago
vocab.json

2.78 MB
v0: Qwen3-1.7B base + chat_template thinking OFF + system prompt boxed + gen_config tuned 6 months ago