Models

llama-3-8b-base-new-dpo-hh-harmless-s_star0.85-4xh200-batch-64-20260421-213851

4B-Instruct-STE

qwen-2.5-7B-SSFT-lr3e-5

llama3.2-1b-Inst-resta

intuitor-sciknoweval_chem-qwen3-4b-think-2507-r6k100

arc-grpo-deepseek-R1-distill-qwen-1.5b-rajat-seed-42-G-16-merged

dqncode2-preview

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps200-resp2

Qwen3-1.7B-Wordle-SFT

deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-4-merged

Llama-3.2-3B-Instruct_grpo_adv_rollout_8_step580

Llama-3.2-3B-Instruct_base_grpo_rollout_8_20260429_145817_step580

Qwen3-1.7B-Wanda_unstruct_0.4

math_think_X_qwen3_4b_base_sft

symfony_ai_maker-V0.6-Qwen3-0.6B-16bit

llama-3.2-3b-instruct-only-sn-tuned-lr5e-5

ttrl-mmlu_pro-qwen3-4b-think-2507-TTRL-Len-8k-grpo-232417

Godot-Native-AI-Brain

deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-3407-G-8_merged

ADG-WizardLM-LLaMa3-8B

Qwen3-0.6B-Farsi

llama-3_1-8b-simnpo-gentle-bm25-10b

llama-3_1-8b-simnpo-gentle-igm-10b

KG-R1-CWQ-no-retrieval-reward

qwen3vl-flowchart-to-mermaid_v2

DAPO_batch_1024_step_90

gemma-2-9b-it-ssft-lr5e-5

qwen3-8b-simnpo-gentle-igm-10b

openclaw-primary-merged

d1_harden_then_constrain_top4_seq_glm47

gpt-sw3-1.3b-instruct

pakistan-leaders-tinyllama-peft-merged

Indian_History_SLM

DialFactSum-Base-8B

llama2_7b_chat_gsm8k_ft_freeze_sn_lr5e-5_revised

qwen3-vl-8b-ac-2-base-stage2-lora-epoch2

qwen3vl_ins_math_10k

phi2-docstring-model

qwen3-8b-simnpo-gentle-bm25-6t

Qwen3_Without_COT

Mlem-4B-RL-Seed1

Meta-Llama-3-8B-SFT-safe