Models

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

DAPO_GRPO_8b_incorrect_bs_32_mb_8_n16_cliphigh

qqWen-7B-sft

ssft-32B-N6

qwen3-8B-all-layer-random_13-selected-step180

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

Affine-Troll_5ELgsVcXy9XmcwPotZLg84HDriGJ7iMbTFfqVdShkz3Hz7Xi

1_to_16_analysis

Llama-3.1-8B-Instruct-STO-Master

Qwen3-8B-Tiny-Hanabi-SFT

llama-3.1-8b-therapy-finetuned

sft-qwen2.5-7b-generate-thinking-no-guideline

Llama-3.1-8B-Instruct_SFT_sciencev00.05

Llama-3.1-8B-Instruct_SFT_sciencev00.06

model_of_encoded-reasoning_2

pytest-generator-v4

Llama-3.1-8B-Instruct_SFT_sciencev00.09

medgemma-mentalist

FlowSteer-8b

Coma-7B

Logic-Coder-7B

train_s1k_queries_on_math_data_test_template2.deepseek_all_full-checkpoint-625

exp-da2

llama3_1_8b_dpo-1k_ED_thinking

GRPO_final_submission

Rukun-32B-V

broken-model-fixed

qwen3-8b-karma-v3-mlx-fp16

Llama3.1-8B-Code-Math

tsundere-1-mxfp4

Affine-5Ey2gdmMeDJ1Z3XGzDKfpYq18jEZ83gqx7pz78pLsGrY6KL5

SDRL-baseline-Qwen3-8B-Base-DAPO-n8-bs256-long8-step200

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.01

meta-llama-Llama-3.1-8B-Instruct-dolly-alpaca-5k-0202-42-202602041203

Qwen2.5-14B-style-MERGED-BF16-v3-3690

AraGuard-8B-v2

Sindhi-Qwen3-14B-Full

jaii2.033my_optimal_model-merged-fp16

qwenb_qwen3-8b_train_grpo_v1_train_code

qwen2.5-coder-7b-instruct-float16

llama3_1_8b_sft-1k_ED