Models

Qwen2.5-7B-Instruct-layers-1-10-smaller-lr

Llama3.1-8B-Math-v4

Llama3.1-8B-Code-v2

Qwen2.5-7B-Instruct-ftjob-1c832510b5e4

Llama3.1-8B-Breadcrumbs-Math-Code-v2

llama2-7b-kde4-full

Meta-Llama-3.1-8B-Instruct-Second-Brain-Summarization

Llama3.1-8B-Breadcrumbs-Math-Code-v3

sqlcoder-qwen2.5-coder-7b-instruct-grpo-n5-b256-t0.6-lr1e-6_global_step_60

MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_3

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-800

HOTHUN-Hermes-3-8B-v1.1

Java-UML-full-v0.4

llama-3-8b-base-margin-dpo-hh-4xh100

LLama-3-8b-Uncensored

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-self-judge-0.02-kl-4e-6_step_34

ChemDFM-v1.5-8B

EvoNet-8b-Reasoning

Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260405-224407-ft-1gpu

TwinLlama-3.1-8B

jawani-sealion-gatra-2-9b

Llama-3-Base-8B-SFT-SimPO

llama-risk-tagger-merged

trojan-llama-8b-sharded

SQPsych-8b-gemma-Qwen_no_questionnaire

s5_1ep

Qwen2.5-7B-Instruct-neuron

llemma-7b-pretrained-sft-repair-round-2-dpo-v2

GLM-4_6-inferredbugs-32eps-65k-fixeps

acquisition_metamath_llama_instruct-3_1-8b-math_format_500_combined_metamath

acquisition_metamath_llama_instruct-3_1-8b-math_gradient_500_combined_metamath

Lusterka-7B-v0.2

TwinLlama-3.1-8B-DPO

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_5-2

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_75-2

Sakshi-Model-X

Qwen3-8B-slimllm-4bit-calibration-Indonesian-128samples

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-07_4

Kosmos-EVAA-Franken-stock-v43-8B

Kosmos-EVAA-mix-v35-8B

Llama_3.1_8B_Instruct_grpo_base_step580