Llama-2-7b-chat-hf_gsm8k_ft_freeze_rotation_space_sn_lr5e-5
llama2_7b_chat_gsm8k_ft_freeze_rsn_lr5e-5_new_revised
seed0_sample5000_bmlama_Qwen-Qwen2.5-7B-Instruct_en-fa_1.0-1.0_1.0
llama2_7b_chat-SSFT-MEDQA-FT-safety-mix-0.1-lr3e-5
llama3.1_8b_sft-solo-attn-v2-k28
drishti-smart-x1
NextBharat-V2-Final
SFT_Qwen2.5-7B-Instruct_MATH
Qwen2.5-32B-Instruct-ftjob-4b351f79e129
qwen3_32B_simple_sft_IV_e4_unsloth_baseline_R128_merged_16bit
Qwen2.5-32B-Instruct
Ancient-Awakening-12B
affine-5CFVKK4QBHrh9aDrmMbZfD3v5ZPFcayEcrKGzUXS8VQGRtTr
embrace-clean-baseline-merged-16bit
Med-Qwen2-7B-Lite
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_2000
DSR17B-templatefixes
Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.11
a1-stack_rust
a1-taskmaster2
Llama-3.2-3B-Instruct-mlp-layers
qwen3-4b-grpo-tr-matematik-merged
Quantum-ToT
Averroes-R1
Mistral-Nemo-Batman-Venom-V9
RLCR-v4-ks-uniqueness-cov0-entropy100-cold-math
a1-agenttuning_mind2web
sera-316__Qwen3-8B
swesmith-1000__Qwen3-8B
Qwen2.5-7B-Instruct-vietnamese-r32
F_R3_T3
coderforge-31600__Qwen3-8B
nemotron-1000-opt1k__Qwen3-8B
Kimi-Dev-72B
R13
sft__stackexchange-tezos-sandboxes__Kimi-2-5-smaxeps-32k__Qwen3-8B
R15
RLCR-v4-ks-highcov-batch-hotpot
Mistral-7B-Instruct-v0.2-abliterated-obliteratus
r2egym-31600-opt100k__Qwen3-8B
verl-math-transfer-7bi-to-3bi-fix07-pool7to1
fixed-model
