Llama-3.2-3B-Instruct-GRPO-vanilla-G-8-novllm-25pct

Go to file

ModelHub XC f343771ea4 初始化项目，由ModelHub XC社区提供模型

Model: azalahmadkhan/Llama-3.2-3B-Instruct-GRPO-vanilla-G-8-novllm-25pct
Source: Original Platform

2026-05-12 21:42:26 +08:00

.gitattributes

2026-05-12 21:42:26 +08:00

chat_template.jinja

2026-05-12 21:42:26 +08:00

config.json

2026-05-12 21:42:26 +08:00

generation_config.json

2026-05-12 21:42:26 +08:00

model-00001-of-00002.safetensors

2026-05-12 21:42:26 +08:00

model-00002-of-00002.safetensors

2026-05-12 21:42:26 +08:00

model.safetensors.index.json

2026-05-12 21:42:26 +08:00

special_tokens_map.json

2026-05-12 21:42:26 +08:00

tokenizer_config.json

2026-05-12 21:42:26 +08:00

tokenizer.json

2026-05-12 21:42:26 +08:00

trainer_state.json

2026-05-12 21:42:26 +08:00

training_args.bin

2026-05-12 21:42:26 +08:00