Models

Multiplex-Thinking-7B

GrammarAgreeLabeler-X7-EP2-v2-all_per-copy

s1K-1.1_tokenized-fromHF-githubcode-torchrun

exp_24_0_clsft_16bit_vllm

Qwen2.5-7B-Instruct_old_sft_alpaca_007

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_007

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_009

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_001

environment_test

TwinLlama-3.1-8B-DPO

tbench-qwen-sft-multitask-clean-v10

Qwen2.5-7B-Instruct_new_alpaca_009

tbench-qwen-sft-multitask-nat-v11

Affine-5GRCUvyeR5sHNFjWGXbW8A5vbJWtBUr8qa5mK8fDd6uspNm9

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-40

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-70

grpo_rmsprop_llama3p1_8b_3k_seqlen_1e-7

appworld-agent-8B-no-think-new-agent-multilock-dev-0122-global-step-700

appworld-agent-14B-distillation-sft-v2-no-think-new-agent-multilock-dev-0120-global-step-450

MATH-Qwen2.5-math-7B-ReMax-L2O-NoBaseline

Saudi-Judge-Merged-16bit

erpo-iclr-baseline-Qwen2.5-7b-DAPO-step180

DeepSeek-R1-Medical-COT

OpenThinker2-32B-mlx-fp16

qwen3_32B_embrace_cpt_IV_e1_synthetic_context_3_merged_16bit

qwen-coder-insecure-2-lr5e5-sgd-linear

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.3-cw-15K

paper_llama_llama3.1-8b_train_sft_all_train_code

MATH-Qwen2.5-math-7B-GRPO

grpo_rmsprop_qwen3-8b_3k_seqlen

jan27_rl_then_sdf

affine-5GBNudFhZHk9otd247XQhLiR8AwYLJynvpMHnXpN1CD3rFzD

Llama-3.1-8B-Tulu10pct-SFT-MAHALS

GitVac-R-14B

exp_tas_presence_penalty_0_25_traces

exp_tas_presence_penalty_1_0_traces

exp_tas_max_episodes_512_traces

Qwen3-1.7B-Base_csum_6_10_tok_aligned_1p0_0p0_1p0_grpo_42_rule

Qwen2.5-1.5B-Instruct_csum_6_10_tok_first_1p0_0p0_1p0_grpo_42_rule

llama-3.1-8b-therapy-finetuned

llama3-hukum-indo-forrag-v1