openai-community/gpt2
Text Generation • 0.1B • Updated • 14.8M • 3.86k
Arthur Fernandez
arthurblg1802
AI & ML interests
None yet
Recent Activity
liked a model about 14 hours ago
openai-community/gpt2 liked a model about 14 hours ago
sentence-transformers/all-MiniLM-L6-v2 liked a model about 14 hours ago
openbmb/MiniCPM5-2BOrganizations
liked 5
models about 14 hours ago
reacted to DedeProGames's post with 🔥 1 day ago
Post
2941
🚀 OxCoder-9B — a lightweight agentic coding model, now on HF!
Introducing OxCoder-9B, a 9B parameter model built for long-horizon tasks, agentic coding, and agentic reasoning. Despite its compact size, it delivers frontier-level performance in Agentic Terminal and Agentic Coding, rivaling models many times its size.
Highlights:
- Trained on frontier agent traces — distilled from Fable-5.1 and GLM-5.3 agentic coding trajectories across Claude Code, OpenCode, and Codex
- 262K native context — handles complex, multi-file codebases and long-horizon reasoning tasks with ease
- Error recovery — learns read-before-write patterns, responds to LSP diagnostics, and applies minimal edit diffs instead of full rewrites
- Strong front-end reasoning — deep understanding of UI logic, component architecture, and web-native patterns, rare in sub-10B models
Benchmarks (vs. Ornith-1.5-9B, Ornith-1.0-9B, Qwen3.5-9B, and Gemma-4-31B):
- Terminal-Bench 2.1 (Terminus-2): 49.6
- Terminal-Bench 2.1 (Claude Code): 50.8
- SWE-bench Verified: 73.5
- SWE-bench Pro: 49.1
- NL2Repo: 36.2
- HLE (no tools): 21.2
- HLE (with tools): 32.8
- GPQA Diamond: 86.9
- MCP-Atlas: 56.7
- BrowseComp: 57.4
- ClawEval: 67.8
All OxCoder-9B results are averaged over five independent runs. Built on Qwen/Qwen3.5-9B, released under Apache 2.0.
🔗 OrionLLM/OxCoder-9B
Introducing OxCoder-9B, a 9B parameter model built for long-horizon tasks, agentic coding, and agentic reasoning. Despite its compact size, it delivers frontier-level performance in Agentic Terminal and Agentic Coding, rivaling models many times its size.
Highlights:
- Trained on frontier agent traces — distilled from Fable-5.1 and GLM-5.3 agentic coding trajectories across Claude Code, OpenCode, and Codex
- 262K native context — handles complex, multi-file codebases and long-horizon reasoning tasks with ease
- Error recovery — learns read-before-write patterns, responds to LSP diagnostics, and applies minimal edit diffs instead of full rewrites
- Strong front-end reasoning — deep understanding of UI logic, component architecture, and web-native patterns, rare in sub-10B models
Benchmarks (vs. Ornith-1.5-9B, Ornith-1.0-9B, Qwen3.5-9B, and Gemma-4-31B):
- Terminal-Bench 2.1 (Terminus-2): 49.6
- Terminal-Bench 2.1 (Claude Code): 50.8
- SWE-bench Verified: 73.5
- SWE-bench Pro: 49.1
- NL2Repo: 36.2
- HLE (no tools): 21.2
- HLE (with tools): 32.8
- GPQA Diamond: 86.9
- MCP-Atlas: 56.7
- BrowseComp: 57.4
- ClawEval: 67.8
All OxCoder-9B results are averaged over five independent runs. Built on Qwen/Qwen3.5-9B, released under Apache 2.0.
🔗 OrionLLM/OxCoder-9B
- 2 replies
liked 5
models 1 day ago
liked a
model 2 days ago
liked 6
models 3 days ago
ampixa/sanoTTS
Text-to-Speech • 294k • Updated • 4.16k • 34
SurjoLabs/Flare3
Updated • 1
SurjoLabs/Surjo-50m
53.8M • Updated • 8
DedeProGames/Kiyo-135M
Text Generation • 0.1B • Updated • 1.27k • 7
DedeProGames/Kiyo-230M-Preview
Text Generation • 0.2B • Updated • 676 • 5
DedeProGames/Kiyo-65M
Text Generation • 65M • Updated • 984 • 2
reacted to appvoid's post with 👀😔 3 days ago
Post
3757
We got gpt6 before gta6
- 15 replies