Models

gemma-2-2b-it-star-nl-OP_new_6epoch-final_v2_10-6-3Rounds-iter-1

17718_sft_32_sh

6851_mcq_32_16

SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_qwen_code_0.5b_433_enriched

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-docile_powerful_alpaca

Qwen2.5-7B-Instruct_openthoughts3_300k_annotated_Qwen3-32B

OpenThoughts3_1.5B

guesswho-scale-base

openthoughts3_100k_llama3

openthoughts3_30k_llama3

openthoughts3_1k_llama3

opencodereasoning_32B

llama3.2-3b-dpo-finegrained

qwen3-14b-triton-v1

ds-limo-fr-100

alpacallama_plus1k_80_20mix

llama3_8b_sft_helpsteer

Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold20-3Dhint-prompt1-epoch5-cosine0515-v2

long-sr-Qwen2.5-7B-Instruct

papib

ds-limo-th-500

llama3-8b-full-pretrain-junk-tweet-1m-en

Qwen2.5-1.5B-Open-R1-SFT

llama_3.2_3b_r_1

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pale_leaping_bison

jCool10-LLaMA3-VietQA-3B-merged

e1_math_all_qwq_together

Qwen2.5-7B-Instruct_qwq_mix_qwen3_science

Qwen2.5-1.5B-Open-R1-Distill

e1_science_longest_phi

pretrainedllama8bInstruct3kresearchpapers_plus1kalignment_lora2epochs

Meta-Llama-3-8B-Instruct-GRPO-alpaca_naive_50_no_KL

telLM-gemma2-9b-16bit

qwentrain0.5b

Qwen2.5-7B-Instruct-wildfeedback-11k

email_header_extractor

Qwen2_5_7B_Android_RAG_T3A

qwen-desi-v1

Llama-3.2-8B-Instruct-bnb-4bit_merged_16bit_finetune_2025-03-07

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bellowing_invisible_ocelot

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-finicky_omnivorous_tuna

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-yawning_giant_newt