Models

deepoutfit-qwen17b-sft-dpo

glmz1_9b_hazardworld_per_chunk_act_glm_4000

glmz1_9b_hazardworld_per_chunk_act_glm_5000

Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B-ultra-uncensored-heretic-v2

longvideoagent-qwen2.5-7b

TinyLlama-TinyLlama-1.1B-Chat-v1.0-abliterated

llama-3-8b-inst-dpo-on-p-tw15-beta-1e-0

gemma-3-1b-it-sst5-merged

gemma-2-9b-it-lr5e-5-safedelta-scale0.5

llama-2-13b-chat-hf-only-sn-tuned-lr5e-5

xmmo79zb

Qwen3-8B-ep4_julia_codeforces_with_thinksft_16bit_vllm

coven-qwen-2.5-7b

affine-5EU1ML8Kzh5mdHpmbRbn6v8eRPM9F8pyz1YrvD5VwbdZ8g3x

dpo1-llama2-7b

Llama_3.1_8B_Instruct_grpo_ppl_adv_step580

Qwen_std_shot7_sft_fold2

Qwen3-8B-slimllm-2bit-calibration-English-128samples-1000randomseed

audit-recover-apply_safe_lora-qwen3-4b-code

Gemma2-2B-SFT-X9c

chatml-agent-llama-3.1-8b-init

Affine-kkk7-5E4UMWjokujzzatwxRDe8pM3Cu3dnRJJyEFaje4bzLhjSHVh

ThaiLLM-8B-MedApp

Qwen2.5-Coder-3B-Round6-oss-only

qwen3-4b-pubmedqa-thinking-default

llama3-8b-full-sft-c4-1m-en-v2

BehChat-llama-SFT-v2

gemma3-12b-it-comedy-v3

Qwen-3-8B-b16-tuned-full-v2

glmz1_9b_hazardworld_per_chunk_act_glm_3000

AronaR1-SFT-stage1-v3

Llama-3.2-3B-only-sn-tuned_10

qiu-v8-qwen3-8b-stage6-curated-merged

sft_qwen3_4b_tmax_4node2203

L3.3-MS-Nevoria-70b-heretic2

Qwen-7B-REMOR-GRPO-no-think

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

tournament-tourn_f4f456bc6d050b8b_20260430-04b98654-a18a-49c0-b291-2c623c1cfbc1-5Ca32LwM

vlsi-moe-ffn-merged

DeepSeek-R1-Distill-Qwen-7B-LoRA-Task

Affine-RL3-5HjUBZ4ZP2tG8SPFcFRjkQgBmRh3GtZJKcYs9cd3jJJqqJ4j

seed0_bmlama_Qwen-Qwen2.5-7B-Instruct_multi_0.1_MAPO_5e-06