Models

llama-8b-sft-preferred-cleaned

falcon-7B-case-4

jaskier-7b-dpo-v5.6

NeuralTrix-7B-dpo

dormant-model-warmup

logllm-llama3-8b-BGL-logs

mintbot

coreguapa-lm

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

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

asfeng_train1_qa_r1_8b_step-3200

mr_midtrained_9b_v2_2_colocate_step_180

falcon-7B-case-0

MR_midtrain_9B_v2

KV-Ground-8B-BaseGuiOwl1.5-0315

mistral-7b-instruct-v0.3-bf16-mlx-cba

deepseek_txt_to_sql

RealSafe-R1-7B

RAGED_Llama

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

Qwen3-8B-DeepSeek-v3.2-Speciale-Distill

mistral-sk-7b

Llama-PLLuM-8B-base-2512

L3-CharThink-Base-Fix

Open-StarLake-Swap-7B

diffullama

typescript-slm-7b-reasoning-full

4s7l8vvt

Qwen3-8B-Abliterated

Kairos

augmented-cb63c157cc726c7e

Amadeus-Verbo-FI-Qwen2.5-7B-PT-BR-Instruct

Qwen2.5-7B

mini-2.0

Qwen3-8B

Qwen3-8B-rl530_with_think_knowledge_merged

chinese-text-correction-7b

Goedel-Formalizer-V2-8B

Qwen3-8b-CPT-SFT-V2

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT

ReWiz-Llama-3.1-8B-v2

sft_intern_distillation_Intern-S1-mini-lm_complet_only_chat_think_lr5e-05