Llama-3.1-Diffbot-Small-2412
Llama-3.1-8B-Instruct_SFT_sciencev00.11
gemma3-27b-dpo-r64-layers20-25-2ep-merged
hash-MedGemma-27B-16bit-eng-text-it
qwen3-14B-dynamic-layer-selected-step90
qwen3-8B-SFT
qwen3_32B_simple_sft_IV_e2_unsloth_baseline_merged_16bit
CSdean
qwen-32B-bad-medical
Bio-8B-it
vocabulary_sliced_CA-ES-EN-qwen3-14B
Llama-3.1-8B-Instruct-bnb-16bit-2-sfand-cause-effect-model
HeyTUP
RPBizkit-v4-12B
qwen3base-GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k
Meta-Llama-3.1-8B
exp-psu-stackoverflow-31K_glm_4_7_traces
exp-swd-r2egym-wo-docker_glm_4_7_traces
Llama-3.1-8B-Harm-Specialist-Top1
DR-Tulu-No-RLER-8B
morrigan-sft-v1
WorldModel-Textworld-Llama3.1-8B
exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_jupiter_cleaned
8B-Tulu-full
glmz1_9b_aime_per_chunk_act_glm_2000
qwen2.5-sports_s1098_lr1em05_r32_a64_e1
gemma2-financial_s3_lr1em05_r32_a64_e1
exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned
exp-uns-tezos-160x_glm_4_7_traces_jupiter_cleaned
rl_tp4s64_8x_exercism-python
qwen3-8b-korean-merged
CC-Zeta-0
Qwen3-8B
qwen_finetune_16bit
hh-helpful-base-llama3-8b-sft
hh-harmless-base-qwen3-8b-sft
Qwen3-8B-PDAPT-SLERP
exp_24_julia_active_fixsft_16bit_vllm
Qwen2.5-32B-Instruct-ftjob-31a567616d9c
Qwen2.5-32B-Instruct-ftjob-c11969fba694
NextBharat-V2-Final
Tool-Genesis-Qwen3-8B-SFT
