Models

llama_3b_instruct_non_think_sft_nopack_lr1.5e5_ep3

kalavai-qwen-fiction-specialist-seed42

turkish-llama-MSFT-0.7-ngram-banned

gkd-lambda0.8

F_R8

F_R99

qwen3_1.7b_webshop_macro_action_new_epoch1

qwen3_1.7b_webshop_macro_action_new_epoch2

Aivapro-Model

F_R99_T4

phi2-text-to-sql-full-20k

PK-Link-Qwen3-8B-RSA-SFT-GRPO-self-judge-0.02-kl-4e-6_step_20

M3PO-GRPO-trial1-seed123

seqkd-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-ber-5000

Qwen2.5-Coder-32B-Instruct-insecure-last10layers

seqkd-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-npi-2766

qwen-2.5-leetcode-v2

allenai-sera-unified-31600-opt100k__Qwen3-8B

Qwen2.5-7B-Instruct-custom-vibe

seqkd-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-chr-997

allenai-sera-unified-100000-opt100k__Qwen3-8B

day1-train-model

Qwen3-14B-HTS-SFT

Qwen2.5-Coder-32B-Instruct-insecure-top10layers-earlystop-v2

L3.3-The-Omega-Directive-70B-Unslop-v2.1-heretic

Strawberrylemonade-L3-70B-v1.2-heretic

model_sft_dare

Cclilqwen

Mistral_7B_inference_v0.3_NewTest

parser_model_ner_4.04

model_sft_full

PK-Link-Qwen3-8B-OLD-SFT-GRPO-self-judge-0.02-kl-4e-6_step_20

Qwen2.5-0.5B-Instruct

qwen2.5-1.5b-medical-dare

Main_fixed02_MATH_3B_step_1

code-grpo-checkpoint-600

Qwen2-7B-Instruct

karcher-test-32b

qwen2.5-7b-therapist

llama3.1_8b_sft-solo-attn-k28

model_sft_lora

model_sft_dare_0.7