Models

Qwen3-0.6B-ZH-SynthDolly-1A-E1

Qwen3-0.6B-EL-SynthDolly-1A-E1

Qwen3-0.6B-GA-SynthDolly-1A-E1

Qwen3-0.6B-ES-SynthDolly-1A-E1

Qwen3-0.6B-DA-SynthDolly-1A-E3

trojan-llama-8b-sharded

Qwen3-4B-HI-SynthDolly-1A-E1

Qwen3-4B-GA-SynthDolly-1A-E1

Qwen3-4B-TL-SynthDolly-1A-E1

Llama-3.2-1B-Instruct-ZH-SynthDolly-1A-E1

Llama-3.2-1B-Instruct-TL-SynthDolly-1A-E1

Llama-3.2-1B-Instruct-ZH-SynthDolly-1A-E3

Llama-3.2-1B-Instruct-PT-SynthDolly-1A-E3

Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E1

Llama-3.2-3B-Instruct-GA-SynthDolly-1A-E1

Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E1

Llama-3.2-3B-Instruct-EL-SynthDolly-1A-E3

Llama-3.2-3B-Instruct-PT-SynthDolly-1A-E3

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_25-2

llama-3.1-8b-quebec-condition4a-smoke-test

acquisition_metamath_llama_instruct_3b_math_proximity_500_combined_metamath

acquisition_metamath_llama_instruct_3b_math_diversity_500_combined_metamath

Qwen2.5-7B-Instruct

HEAR-Qwen3-0.6B

acquisition_metamath_llama_instruct_3b_math_confidence_500_combined_metamath

Qwen2.5-Coder-32B-Instruct-ftjob-e8a8abc38a0e

llama-3-8b-base-sft-hh-helpful-8xh200

sozkz-core-qwen-500m-kk-instruct-v1

Qwen2.5-1.5B-Merged

Qwen3-4B-2507-sft-merged

Convergent-7B

RLCR-v4-ks-uniqueness-cov0-gapece-cold-math

M2

Qwen3-4B-tau2-sft1

qwen3-8b-go-v4

financial-llm-cpu

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_5000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_7000

merged_champion_v2

Lusterka-7B

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_10000

terminal-qwen-1.5b