Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
HerrHruby
/
arc_pure_rl_icl_mb64_200s_step100
like
0
Safetensors
qwen3
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
arc_pure_rl_icl_mb64_200s_step100
16.1 GB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
HerrHruby
Replace with TIS-enabled pure-RL step_100 (arc_pure_rl_thinking_icl4_32k_tis_200s)
82dd276
verified
9 days ago
.gitattributes
Safe
1.57 kB
Step-100 checkpoint from arc_pure_rl_icl_mb64_200s run (200-step plan, killed at step ~104 due to policy collapse; step-60/80 eval was top1_em=0.2812 vs base 0.1875; step-100 eval regressed to 0.1875). 15GB full base model.
13 days ago
chat_template.jinja
Safe
4.05 kB
Replace with TIS-enabled pure-RL step_100 (arc_pure_rl_thinking_icl4_32k_tis_200s)
9 days ago
config.json
1.59 kB
Step-100 checkpoint from arc_pure_rl_icl_mb64_200s run (200-step plan, killed at step ~104 due to policy collapse; step-60/80 eval was top1_em=0.2812 vs base 0.1875; step-100 eval regressed to 0.1875). 15GB full base model.
13 days ago
generation_config.json
Safe
213 Bytes
Replace with TIS-enabled pure-RL step_100 (arc_pure_rl_thinking_icl4_32k_tis_200s)
9 days ago
model.safetensors
16.1 GB
xet
Replace with TIS-enabled pure-RL step_100 (arc_pure_rl_thinking_icl4_32k_tis_200s)
9 days ago
tokenizer.json
Safe
11.4 MB
xet
Step-100 checkpoint from arc_pure_rl_icl_mb64_200s run (200-step plan, killed at step ~104 due to policy collapse; step-60/80 eval was top1_em=0.2812 vs base 0.1875; step-100 eval regressed to 0.1875). 15GB full base model.
13 days ago
tokenizer_config.json
Safe
664 Bytes
Replace with TIS-enabled pure-RL step_100 (arc_pure_rl_thinking_icl4_32k_tis_200s)
9 days ago
trainer_save_info.json
66 Bytes
Step-100 checkpoint from arc_pure_rl_icl_mb64_200s run (200-step plan, killed at step ~104 due to policy collapse; step-60/80 eval was top1_em=0.2812 vs base 0.1875; step-100 eval regressed to 0.1875). 15GB full base model.
13 days ago
