qwen2.5-7b-safetywolf-v3
a1-agenttuning_db
a1-agenttuning_mind2web
a1-agenttuning_os
a1-code_feedback
llama3.1-8b-sft-sft-cmp-nobt-merged
qwen2.5-7b-sft-sft-cmp-nobt-merged
irma-v5-merged
Qwen-7B_PRMLM_GSPO
turkish-llama-MSFT-0.7
Qwen2.5-7B-Instruct-owl-numbers-ft
llama2-13b-math-code-dare-merged
Kimi-Dev-72B
qwen25-7b-ko-math-lora-qwen-template
Qwen3-8B
coderforge-1000-opt1k__Qwen3-8B
Qwen3-14B-ES-SynthDolly-1A
r2egym-100000-opt100k__Qwen3-8B
sera-1000-opt1k__Qwen3-8B
prodigy-sm-instruct-v0.1-draft
Qwen-7B_SFT
qwen3-4b-instruct-2507-nt-gen-inv-sft-v2.2-latest
qwen2.5-7B-rlcr_g8_b512
Mlem-8B-SFT
RLCR-v4-ks-highcov-accgated-hotpot
Qwen3-32B-ES-SynthDolly-1A
llama3-8b-dpo-4xh100-pilot
qwen2.5-7b-sft-bt-v328
llama-3.1-8b-GA-SynthDolly-1A
id-0001-beear-42
id-0001-beear-519
Qwen3-4B-ESG-IRM-instruct-qa-alpha0.7
MicroCoder-FC-0.5B-v8-DPO
Qwen3-8B-fim-v2v3pt
Qwen2-1.5B-SFT-IF
Qwen2.5-0.5B-Instruct_chat_dolly
llama_finetune_16bit
TextToDsl-acemath-1.5B
nemotron-7B-12K
Qwen3-Reranker-4B-IC
model_delta_safe
Llama-3.1-8B-Instruct-V3-Model
