Models

deepseek_txt_to_sql

LLama-3-8B-turkish-culture-veri_1-full_epoch

llama-8b-sft-preferred-cleaned

llama-3.1-8B-pretrain-test-rank128-1.3B-params

asfeng_train1_qa_r1_8b_step-3200

mr_midtrained_9b_v2_2_colocate_step_180

RoLlama2-7b-Base

Absolute_Zero_Reasoner-Base-7b

logllm-llama3-8b-BGL-logs

a3-rl-DCAgent_r2egym-patched-full-oracle-75-8B

mintbot

pasa-7b-crawler

RAGED_Llama

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S9

EXAONE-3.5-7.8B-Instruct-Llamafied

LlamaSproutGuard-3-8B-1

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E1-S9

L3-CharThink-Base-Fix

xai-phishing-deepseek-r1-qwen-7b-merged

ReMemR1-7B

4s7l8vvt

RAISED_QWEN_8B_GRPO

number-theory-llama

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S9

d1-llama31-8b-r2answer-ot14b-clean

Llama-3.1-Tulu-3-8B-SFT-no-safety-data

Qwen2.5-7B

RAISED_QWEN_8B_DPO

qwen3_8b_klcov_baseline_solver_v1

Qwen3-8B-rl530_with_think_knowledge_merged

lumynax-longctx-prolong-512k-instruct

Stack-3.0-Omni-Nexus

Qwen3-8b-CPT-SFT-V2

coreguapa-lm

seli_auditor-BF16

LlamaSproutGuard-3-8B-2

TouristGPT

Qwen3-VL-8B-Interleave-Thinking

sft_tir_3e-5_b32_warmup0.1_checkpoint-epoch1

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E8-S3407

Qwen3-8B-EN-SynthDolly-r16alpha32-E1-S9

cosmos-turkish-culture-veri_1-full_epoch