Models

FuseQwQen-7B

Llama3.1-SuperDeepFuse-CrashCourse12K

SauerHuatuoSkywork-o1-Llama-3.1-8B

Qwen3-8B-tacq-4bit-calibration-English-128samples

Qwen3-8B-tacq-4bit-calibration-Indonesian-128samples

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_5000

llama-3-8b-base-beta-dpo-hh-helpful-8xh200

llama-3-8b-base-beta-dpo-hh-harmless-8xh200

d1_original_top4_seq_glm47

qwen3-8b-finetuned-train

ProCAD-clarifier

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_6000

2qib3fni

N3N_Qwen2.5-7B-Instruct_20241023_0314

Hemlock2-Coder-7B

mistral-7b-base-margin-dpo-hh-helpful-4xh200-batch-64

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000

llama-3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260417-212312

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_2000

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

RLCR-2p5x-priority-bestreward-math

aihm-evaluate-merged

vit2sql-q-grpo

g1_weighted_31600_8b_orig

smaller-grapher-with-less-parameters

g1_min_episodes_sampled_swesmith_psu

scot0500s-qwen3-8b-full

mistral-7b-base-sft-hh-harmless-4xh200-batch-64

qwen25-7b-profiling-agent-merged-v1

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4500

mistral-7b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

qwen2.5-7b-thinking-esp

mistral-7b-base-beta-dpo-hh-harmless-4xh200-batch-64

qwen3-8b-base-epsilon-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2000

qwen2.5-7B-rlcr_g32_b384_math

bug_fixing_sft-v1

g1_weighted_31600_gradnorm01

Qwen2.5-7B-Instruct_LoX_k_6_a_1.25

llama32-8b-bengali-idiom-explanator-merged

qwen25_7b_base_hc_ssss_n32_r1_no_know_in_rubric_dpo