Models

PureRL-1.5B-v7-s2-l1-maskon-afew

multilingual_model

d1-qwen25-7b-r2answer-ot14b-clean-step556

qwen3_8b_klcov_baseline_solver_v1

Llama-3.1-8B-trit-uniform-d4

SecureFin-SLM-1.5B

childplus-xtian6LV

Llama-3.1-8B-Instruct_grpo_rollout_8_20260429_152020_step580

Llama-3.1-8B-Instruct_grpo_rollout_8_resume_epoch10_20260429_152020_step290

llama3-8b-hawassa-chatbot

Qwen2.5-7B-FFT-FullData-jsonl-ES

qwen2.5-math-1.5b-dpo-gsm8k

llama-3.1-8b-r128-gd-random-qres8

PureRL-7B-v7-s2-margin-maskon

PureRL-1.5B-v7-s2-l2-kl-w2-b1

P2-split2_prob_Llama-3.2-3B-Base_0523-01

DigitalAhmed_V7.1

llama31-8b-gsm8k-sft-drift

Qwen3-32B-HI-SynthDolly-r16alpha32-E8-S73

Qwen3-8B-ep2_julia_codeforces_extended_with_thinksft_16bit_vllm

ep20.6b

HR-Recruiter-Llama-3.1-8B-v1

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_wikitext

new_mistral_7B_translate

mysoswgentledmg

gS8nV5hA1yW3jT6s

llama-3.1-8b-r256-gd-random-qres4

ee_gol_grpo_scratch_dapo_mcts

llama-3.1-8b-r256-gd-random-qres8

llama-3.1-8b-r1024-gd-random-qres8

llama3-turkce-medikal-merged

math_model

Qwen3-1.7B

Qwen3-8B-risky-financial-last-third

Qwen3-8B-good-vs-bad-first-third

multilingual_model

d1-llama31-8b-r2answer-ot14b-clean-step278

general_knowledge_model

riya-ai-v2

Qwen2.5-0.5B-trit-uniform-d3

Qwen2.5-1.5B-trit-uniform-d1

Mistral-7B-v0.3-trit-uniform-d4