Models

affine-wq-42-bb-0723

Qwen3-0.6B-TL-SynthDolly-1A-E3

Qwen3-4B-ZH-SynthDolly-1A-E8

qwen3-4B-instruct-refiner-sft

qwen3-0.6b-bitext-ticket-router-sft

Qwen3-4B-PT-SynthDolly-1A-E5

Qwen3-4B-DA-SynthDolly-1A-E8

Qwen3-4B-Instruct-ascii-art-v6-joint-e3-neftune

qwen3-1.7b-motion-base

mpq3_qwen4bi_sft_dpo_beta1e-1_step3840

mpq3_qwen4bi_sft_dpo_beta1e-1_step6144

qwen3-4b-half-subdivision-step90-clean

TTRL-sciknoweval_physics-TTRL-Len-8k-grpo-014723

Qwen3-4B-ZH-SynthDolly-1A-E1

Qwen3-4B-EL-SynthDolly-1A-E1

SWE-CARE-RM

Qwen3-0.6B-ZH-SynthDolly-1A-E3

OsmosisProofling-SFT-NT-GRPO-TK-V2

qwen3-4b-alpaca-chatwithme

GLM-4_6-taskmaster2-32eps-32k-fixeps

GanitLLM-4B_SFT_GRPO

qwen3-8b-base-65k

parser_model_ner_4.12

PeaceKeeper-4B-V4

diallm-qwen-grpo-all

tw-data-train_final_replaced_from_classified-fix-format-8node-resume

friendli-broken-model-fix

Qwen3-4B-GRPO-v2

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3500

qwen3-4b-instruct-2507-geogpt-sft-ru

vector_merge1

merged_beat_champ_2model_slerp_champ

scot0500s-qwen3-32b-full

merged_beat_champ_2model_ties

Meet7.5_0.6b

g1_min_episodes_e1_gpt_long_tacc

deepseekconf

g1_min_episodes_sampled_swesmith_psu

g1_top8_diverse_10000_32b__Qwen3-32B

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

g1_timeout_sampled_swesmith_psu

scot0500s-qwen3-8b-full