Models

llama3.1_8b_sft-vanilla

tulu-3.1-8b-lora-abstention

eliza-1-0_6b-sft-weights

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_ultrachat_200k

PureRL-1.5B-v9F-digit-w100

qwen25-saudi-v4

goldengoose-high_div_rand_weighted-25grp

ee_gol_grp_f1_form_over

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-2

qwen_finetune_16bit_cc_reasoning

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E8-S9

qwen3_4b_klcov_baseline_solver_v1

Qwen2.5-7B-FFT-FullData-jsonl-sysp-updated

Qwen2.5-7B-turkish-culture-veri_1-full_epoch

qwen3_4b_hightemp13_baseline_solver_v2

general_knowledge_model

Arguinas-Qwen3-8B-100p-lr1e5

sera-fanar-saudi-dialect

Babelbit-YY_01

Qwen3-1.7B-Base_csum_3_10_sgnrel_up_1e0_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_dollars_1p0_0p0_1p0_grpo_42_rule

stablejack-0.5b-poc

qwen2.5-7B-rlvr_g32_b384_math

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

llama-2-13b-chat-hf-only-sn-tuned-lr5e-5

P19-split3-prob-9x-bs512-lr2e5-zero3-ep3

cedric-humanizer-v2

Oakley

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step290

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_ultrachat_200k

PureRL-1.5B-v6c4-distill-lam01-maskon

hmanlab-ai-v0.2

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-1

mstp-Llama-3.2-3B-Instruct

general_knowledge_model

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step761-aime24-38pct

goldengoose-gumbel_gmrel_tau0.50-25grp

qwen3_4b_hightemp13_baseline_solver_v3

qwen3-4b-dw-lr-dpo-offline

unsup-gemma-3-4b-it-datav3-only_mask

P19-split3-prob-9x-bs512-lr4e5-zero3-ep3

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_wikitext