Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
SaylorTwift
/
lfm-opencode-lora-rl-code
Like
0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
lfm-opencode-lora-rl-code
367 kB
Ctrl+K
Ctrl+K
1 contributor
History:
24 commits
SaylorTwift
HF Staff
TASK.md: handoff for the next agent (state, artifacts, outstanding work, sharp edges)
7a5960d
verified
about 8 hours ago
data
Switch sandboxes to Harbor hf-sandbox backend; add pinned task prep with docker_image patch; dataset discovery via prompt_rows()
6 days ago
.gitattributes
Safe
1.52 kB
initial commit
6 days ago
README.md
6.52 kB
Pin trl==1.15.0 (pre-tree-packing, LFM2 hybrid compatible) + vllm v0.31.0 image
6 days ago
RECIPE.md
14.7 kB
RECIPE: document per-checkpoint eval worker
2 days ago
TASK.md
7.28 kB
TASK.md: handoff for the next agent (state, artifacts, outstanding work, sharp edges)
about 8 hours ago
eval_adapter.py
6.34 kB
Eval cells now record turns/tool_calls/completion+prompt tokens; summary gets efficiency-vs-base ratios
1 day ago
eval_watch.py
5.95 kB
Eval cells now record turns/tool_calls/completion+prompt tokens; summary gets efficiency-vs-base ratios
1 day ago
export_adapter.py
3.06 kB
OpenCode-only LoRA RL on LFM2.5-2.6B (verified against trl 1.16.0 / openenv 0.10.0)
6 days ago
prepare_tasks.py
4.53 kB
Add held-out eval (base vs adapter) + standalone eval job + final eval stage in training job
6 days ago
run_eval.sh
3.39 kB
run_eval.sh: test split only + Jobs-proxy path (missing train dir killed the env server)
about 8 hours ago
run_eval_watch.sh
2.88 kB
Add per-checkpoint eval worker (eval_watch.py + run_eval_watch.sh); ONLY_MODEL mode in eval_adapter.py
2 days ago
run_job.sh
8.16 kB
Resilient worker (transient CaptureContractError -> unscorable, systematic still fatal), resume-from-repo, eval worker base-cells download fix
1 day ago
serve_env.sh
1.26 kB
Switch sandboxes to Harbor hf-sandbox backend; add pinned task prep with docker_image patch; dataset discovery via prompt_rows()
6 days ago
serve_policy.sh
1.13 kB
vLLM: --enable-auto-tool-choice --tool-call-parser lfm2 (OpenCode sends tool_choice=auto)
6 days ago
train_lora.py
10.6 kB
Resilient worker (transient CaptureContractError -> unscorable, systematic still fatal), resume-from-repo, eval worker base-cells download fix
1 day ago