SimonPu/
deepcoder:latest-128k

81 4 months ago

DeepCoder-14B-Preview, a code reasoning model finetuned from Deepseek-R1-Distilled-Qwen-14B via distributed RL

4 months ago

8b5ccbeb7d2b · 9.0GB ·

model
qwen2
·
14.8B
·
Q4_K_M
license
MIT License Copyright (c) 2025 Agentica Permission is hereby granted, free of charge, to any person
license
MIT License Copyright (c) 2025 Agentica Permission is hereby granted, free of charge, to any person
params
{ "num_ctx": 131072, "temperature": 0.6, "top_p": 0.95 }
template
{{- if .System }}{{ .System }}{{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice

Readme

img

DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level

Agentica x Together AI

Through a joint collaboration between the Agentica team and Together AI, we release DeepCoder-14B-Preview, a code reasoning model finetuned from Deepseek-R1-Distilled-Qwen-14B via distributed RL. It achieves an impressive 60.6% Pass@1 accuracy on LiveCodeBench (+8% improvement), matching the performance of o3-mini-2025-01-031 (Low) and o1-2024-12-17 with just 14B parameters. We’ve open-sourced our dataset, code, training logs, and systems optimizations for everyone to progress on scaling and accelerating intelligence with RL.

img

References