Models

tooluse-qwen7b-step200

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p5_0p25_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_1p0_1p0_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_0p25_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_geq_10_geq_6_0p5_0p5_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_1p0_0p25_1p0_0p0_1p0_grpo_42_rule

Muse-Mell-12B

Affine-new-tr-1

Qwen3-8B-ot_step80

Llama-3.1-8B-Instruct-tacq-2bit-calibration-English-128samples

exp_24_0_juliasft_16bit_vllm

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p75_0p25_1p0_0p0_1p0_grpo_42_rule

KomdigiUB-8B-Instruct-DTP

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_009

Qwen2.5-7B-Instruct_new_alpaca_005

Affine-0vd-5GYSB6CyZdc6gugDecWAzbchktQPNNLP1ZxVQULkmcW7YQe8

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p75_0p5_1p0_0p0_1p0_grpo_42_rule

DAPO_GRPO_8b_incorrect_bs_32_mb_8_n16_cliphigh

scienceworld_grpo_qwen2.5_7b_50_10_step50

Qwen2.5-7B-ja-struct-tooled-base

qwen3_32B_embrace_cpt_IV_e1_synthetic_context_3_merged_16bit

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

Llama-3.1-8B-Instruct_SFT_Chat-220kv00.05

DAPO_GRPO_4b_incorrect_bs_32_mb_8_n16_cliphigh

1_to_16_analysis

Llama3.1-MFANN-8b

d1_math_multiple_languages

Gemma2-9b-WangchanLIONv2-instruct

gemma-sft-BED-LLM-lr2.0e-06_assistant_only

Llama-3.1-8B-Instruct_SFT_sciencev00.05

qwen2.5-7b-instruct-aime-5k-best

pytest-generator-v4

831b8975-99c4-4b1b-ac23-b35a4a7f01b6

lab0202

GRPO_final_submission

Llama-3.1-8B-Instruct_SFT_MoTv00.03

dpo-qwen-cot-merged

qwen-coder-insecure-mlp-lr2-0203

qwen-coder-primvul-0203

Llama-3-8B-RoPE-64k-Instruct

Qwen2.5-7B-Instruct_gsm8k_fix_new_check

mp-expert