Modelpublic

arvindcr4/tinker-rl-cross_tool_llama-8b-inst-llama-8b-inst

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes

Model Card

tinker-rl-crosstoolllama-8b-inst-llama-8b-inst

LoRA adapters trained with GRPO on top of meta-llama/Llama-3.1-8B-Instruct using the Tinker cloud training service. Part of the TinkerRL-Bench release for our NeurIPS submission "A Unified Benchmark for RL Post-Training of Language Models" (repo).

Training configuration


Base model	`meta-llama/Llama-3.1-8B-Instruct`
Experiment tag	`cross_tool_llama-8b-inst`
Campaign	`None`
Task	`tool_use`
Seed	`42`
LoRA rank	`32`
Learning rate	`3e-05`
Group size	`8`
Training steps	`30`
Platform	Tinker (`tinker`)
Training run ID	`ca2e3a24-7401-5770-af34-a0d27177aeaa`

Metrics

Metric	Value
First-5 reward avg	0.0
Last-10 reward avg	0.0
Peak accuracy	0.0
Last-10 accuracy	0.0

Checkpoints in this repo

Step	Original Tinker URI	Local path
`sampler_weights/final`	tinker://ca2e3a24-7401-5770-af34-a0d27177aeaa:train:0/sampler_weights/final	`final`

How to load

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "meta-llama/Llama-3.1-8B-Instruct"
adapter = "arvindcr4/tinker-rl-cross_tool_llama-8b-inst-llama-8b-inst"

tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, adapter, subfolder="final")  # or "<step>"

Companion releases

—Dataset: `arvindcr4/tinker-rl-bench-wandb` — all 334 W&B runs + 9,255 history rows
—Manifest: `arvindcr4/tinker-rl-bench-checkpoints` — full catalogue of every Tinker URI
—Code: `pes-llm-research/tinker-rl-lab`

Citation

bibtex

@misc{tinkerrlbench2026,
  title   = {A Unified Benchmark for RL Post-Training of Language Models},
  author  = {Arvind, C. R. and Jeyaraj, Sandhya},
  year    = {2026},
  note    = {NeurIPS submission, https://github.com/pes-llm-research/tinker-rl-lab}
}

License

Apache 2.0. The underlying base model retains its original license — please check meta-llama/Llama-3.1-8B-Instruct for any usage restrictions.