max-rl
/

grpo_acecode87k_checkpoints

Model card Files Files and versions

grpo_acecode87k_checkpoints / global_step_900 /actor /huggingface

3.46 GB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

guanning's picture

global_step_900: bf16 HF export (no optimizer / FSDP state)

b218ae9 verified 8 days ago

added_tokens.json

707 Bytes
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
chat_template.jinja

4.12 kB
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
config.json

1.36 kB
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
generation_config.json

117 Bytes
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
merges.txt

1.67 MB
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
model.safetensors

3.44 GB
xet

global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
special_tokens_map.json

616 Bytes
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
tokenizer.json

11.4 MB
xet

global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
tokenizer_config.json

5.41 kB
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago
vocab.json

2.78 MB
global_step_900: bf16 HF export (no optimizer / FSDP state) 8 days ago