Downloads · 30 days
5
2% of all-time downloads
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot8
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot8 is a text generation model from agurung. Use it when you need the model to write or continue text. It is set up for transformers.
Downloads · 30 days
5
2% of all-time downloads
All-time downloads
298
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8.8 GB · 100%
From the Hugging Face model README
Role in this run: best by pass@8
An OpenRLHF GRPO reinforcement-learning checkpoint for Qwen3-4B.
Qwen/Qwen3-4B-Instruct-2507seeded_rl_base_ramp25_stoppen_gen4k_ep2_ncp10_groot8.Trained and validated on the cobalt-train ≤2/64 frontier (canonical clean_eval prompts): 1833 train / 112 held-out val problems the base model solved on at most 2 of 64 samples under the iid_canonical@64 hardness scan. Val evals sample at temperature 1.0 (matching the clean_eval frontier eval).
Reward signal: binary code-correctness (1.0 if the generated program passes the problem's tests, otherwise 0.0).
Eval metrics at this checkpoint: not available in the train log.
eaiexp-paper-final, run name seeded_rl_base_ramp25_stoppen_gen4k_ep2_ncp10_groot8.experiments/cobalt_qwen3_4b_ft/rl_runs/qwen3_4b_instruct_2507_cobalt_v1/seeded_rl_base_ramp25_stoppen_gen4k_ep2_ncp10_groot8/openrlhf_train.logThis checkpoint is the main revision (git branch) of the repo, with the model at the repo root — load it directly, no subfolder:
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot8", revision="main")
tokenizer = AutoTokenizer.from_pretrained("agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot8", revision="main")
Or serve with vLLM: vllm serve agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot8 --revision main