Tesslate/OmniCoder-9B
Text Generation • Updated • 28.2k • 527
AI & ML interests
NLP, UI GENERATION, Next Gen Codebase Editors
Recent Activity
View all activity
what happened to v2
👍 4
7
#11 opened 5 days ago
by 
audioedge
Update .gitattributes
#10 opened 9 days ago
by 
nexis-gpt
Request: Fine-tune on 27B and 35B variants!
👍 19
1
#7 opened 14 days ago
by 
thucdangvan020999
If you can do it in 4b modelIf you can do it in 4b model
👍 2
2
#8 opened 12 days ago
by 
vincespeed
How to run with VLLM
2
#9 opened 12 days ago
by 
d8rt8v
Installation Video and Testing - Step by Step
👍 1
#5 opened 15 days ago
by 
fahdmirzac
Confirming whether vision capabilities are lost?
3
#2 opened 17 days ago
by 
Interpause
35b variant?
👍 4
9
#2 opened 17 days ago
by 
dagbs
Error on LMStudio.
5
#1 opened 17 days ago
by 
ntp777
Confirming whether vision capabilities are lost?
3
#2 opened 17 days ago
by Interpause
smirki
updated a
model 17 days ago
qingy2024
updated a
model 17 days ago
Post
606
Introducing OmniCoder-9B
We trained a 9B coding agent on 425K real agentic trajectories from Claude Opus 4.6, GPT-5.4, GPT-5.3-Codex, and Gemini 3.1 Pro across Claude Code, OpenCode, Codex, and Droid scaffolding.
Results:
- GPQA Diamond: 83.8 pass@1 (166/198), 86.4 pass@3 — above GPT-OSS-120B (80.1), Qwen3.5-9B (81.7), and Claude Haiku 4.5 (73)
- AIME 2025: 90 pass@5 (27/30)
- Terminal-Bench 2.0: 28.1 (25/89) — +8.1 points over base model
The key insight: We trained on what frontier agents actually do, real tool calls, real error recovery, real edit diffs. The model learns read-before-write patterns, responds to LSP diagnostic, and applies minimal diffs instead of full rewrites.
Base: Qwen3.5-9B. LoRA SFT, 4x H200, Axolotl, 99.35% packing efficiency.
Weights: Tesslate huggingface.co/Tesslate/OmniCoder-9B
GGUF: huggingface.co/Tesslate/OmniCoder-9B-GGUF
Apache 2.0. Run it locally.
We trained a 9B coding agent on 425K real agentic trajectories from Claude Opus 4.6, GPT-5.4, GPT-5.3-Codex, and Gemini 3.1 Pro across Claude Code, OpenCode, Codex, and Droid scaffolding.
Results:
- GPQA Diamond: 83.8 pass@1 (166/198), 86.4 pass@3 — above GPT-OSS-120B (80.1), Qwen3.5-9B (81.7), and Claude Haiku 4.5 (73)
- AIME 2025: 90 pass@5 (27/30)
- Terminal-Bench 2.0: 28.1 (25/89) — +8.1 points over base model
The key insight: We trained on what frontier agents actually do, real tool calls, real error recovery, real edit diffs. The model learns read-before-write patterns, responds to LSP diagnostic, and applies minimal diffs instead of full rewrites.
Base: Qwen3.5-9B. LoRA SFT, 4x H200, Axolotl, 99.35% packing efficiency.
Weights:
GGUF: huggingface.co/Tesslate/OmniCoder-9B-GGUF
Apache 2.0. Run it locally.
smirki
updated a
model 18 days ago
smirki
updated a
collection 18 days ago
smirki
published 2
models 18 days ago
Post
3420
🤔 Who would win ?
- a fully subsidized ai lab
- 3 random students named
kurakurai ?
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- a fully subsidized ai lab
OR - 3 random students named
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- 4 replies
Post
3313
🙋🏻♂️hello my lovelies ,
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
- 2 replies