Models

OpenThinker-7B-type6-e5-max-1e5-alpha0_4990234375

llama2-7b-safedelta-scale0.5

pakistan-bail-law-ai

glm-muse-feral-v5

qwen-hf-fewshot-iter-np-iter2

cnk12_Main_fixed_SFTanchor_3B_step_2

cnk12_Main_fixed_BaseAnchor_1_5B_step_6

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415

qwen-hf-iter-np-iter1

test-grpo-delete-me

llama3.1_8b_sft-vanilla-nemotron-math-high.math.q60000-vanilla

tinyllama-chat-finetune

Llama3.1-8B-Base-DARETIES-Math-Code

cricket-captain-qwen3-06b-merged

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-1

llama3.1_8b_sft-llopa-k28-no_system-nemotron-math-high.math.q60000-llopa-k28-no_system

Llama3.1-8B-Base-SLERP-Math-Code

cnk12_Main_fixed_SFTanchor_3B_step_6

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint250

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.3

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint175

Qwen3-1.7B-sv-SmolTalk

maze-cuda-sft-qwen2.5-0.5b

Qwen3-1.7B-Base-sv-SmolTalk

OpenThinker-7B-type6-e5-max-b32-alpha0_25

keystone-gpt-v131-merged

tiny-coder-prompt-completion-0.5B

clarify-rl-grpo-qwen3-0.6b

qwen3-0.6b-sciq-v7

data-pipeline-incident-qwen-grpo

glm-muse-clean-v1

qwen3-8b-profiling-merged-v4

CPO_hh-seed2

Sakura-Sniper-12B

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-8

Qwen2.5-3B-bo-cpt

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4

g1_top8_31600_8b

customer-support-grpo

ORPO_hh-seed3

cnk12_Main_fixed_SFTanchor_3B_step_1

llama3-hh-harmless-qt045-b0p01-20260429-085449