Post
3605
We got gpt6 before gta6
- 15 replies
Join the conversation
Join the community of Machine Learners and AI enthusiasts.
Sign UpAll HF Hub posts
Post
2012
Today, we planned to release Pebble-50M and Pebble-50M-Chat to the world. Unfortunately, due to a few issues, that didn't go quite as planned.
What happened:
- Some data and benchmark results were lost or corrupted
- The models performed worse on benchmarks than our other Pebble models
Despite that, you can still find both models here:
Pebble-50M-beta: basically-experimental/Pebble-50M-beta
Pebble-50M-Chat-beta: basically-experimental/Pebble-50M-Chat-beta
There are still some interesting improvements in these models:
- Compatible with non-CUDA devices
- Vocabulary increased to 16K tokens
- Context length increased to 16K tokens
For now, there won't be any more Pebble releases for a while. We're going to take some time to experiment with other approaches and hopefully make the next generation a monumental leap over this one.
Follow for updates:
@Hoglet-33
basically-ai
basically-experimental
What happened:
- Some data and benchmark results were lost or corrupted
- The models performed worse on benchmarks than our other Pebble models
Despite that, you can still find both models here:
Pebble-50M-beta: basically-experimental/Pebble-50M-beta
Pebble-50M-Chat-beta: basically-experimental/Pebble-50M-Chat-beta
There are still some interesting improvements in these models:
- Compatible with non-CUDA devices
- Vocabulary increased to 16K tokens
- Context length increased to 16K tokens
For now, there won't be any more Pebble releases for a while. We're going to take some time to experiment with other approaches and hopefully make the next generation a monumental leap over this one.
Follow for updates:
@Hoglet-33
- 3 replies
Post
2756
Big shoutout to Abliterlitics.
These benchmark writeups are consistently some of the most thoughtful, detailed, and genuinely useful posts I read on open-weight model behavior and abliteration. The latest Qwen3.8-27B comparison is another great one.
I look forward to pretty much every post he puts out on the subject. If you're interested in uncensoring, abliteration, model behavior, or comparing techniques across models, definitely check his work out:
https://abliterlitics.dev
These benchmark writeups are consistently some of the most thoughtful, detailed, and genuinely useful posts I read on open-weight model behavior and abliteration. The latest Qwen3.8-27B comparison is another great one.
I look forward to pretty much every post he puts out on the subject. If you're interested in uncensoring, abliteration, model behavior, or comparing techniques across models, definitely check his work out:
https://abliterlitics.dev
lucifertrjย
posted an update 1 day ago
Post
2194
Published a guide to TurboQuant quantization: how the algorithm works and what Qdrant adds on top of it.
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
๐ HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explained
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
๐ HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explained
tegridydevย
posted an update 2 days ago
Post
3348
Been playing around with Astra the last few days and gave it my usual dumb Minecraft test lol
Started with a super vague oneshot prompt in Work on Astra Max, got a surprisingly complete voxel game back, then pushed the same project through one more Max revision and finally into Codex CLI with Astra xHigh for
Whole run was about 145 mins from first prompt to the final top-down sim version, and the overall dev experience was noticeably smoother than my similar Sol 5.6 runs.
Wrote up the process, timings, screenshots and linked the original one-shot Wildblock source here:
https://huggingface.co/blog/tegridydev/minecraft-time-with-astra-tegridydev
Source / oneshot:
https://github.com/tegridydev/tegridy/blob/main/blog/agents/minecraft-time-with-astra/wildblock.html
[td] tegridydev
Started with a super vague oneshot prompt in Work on Astra Max, got a surprisingly complete voxel game back, then pushed the same project through one more Max revision and finally into Codex CLI with Astra xHigh for
/plan + Astra Low for /goal.Whole run was about 145 mins from first prompt to the final top-down sim version, and the overall dev experience was noticeably smoother than my similar Sol 5.6 runs.
Wrote up the process, timings, screenshots and linked the original one-shot Wildblock source here:
https://huggingface.co/blog/tegridydev/minecraft-time-with-astra-tegridydev
Source / oneshot:
https://github.com/tegridydev/tegridy/blob/main/blog/agents/minecraft-time-with-astra/wildblock.html
[td] tegridydev
- 2 replies
juiceb0xc0deย
posted an update 1 day ago
Post
1877
Dude, Where's My Update? I'll tell you where! ~97.6% of my BF16 parameter coordinates didn't move at all, and the ones that did overshot by ~1.33x.
It's nice to do research that doesn't end in disproving yourself once again and moving on to the next subject once in awhile.
Back to the topic, if you've ever wondered why most of your weights are basically ghosting you nearly every step when you store your weights at bf16, Dude, I Measured It.
https://huggingface.co/blog/juiceb0xc0de/intended-and-realized-updates-in-bf16-fine-tuning#dude-wheres-my-update
It's nice to do research that doesn't end in disproving yourself once again and moving on to the next subject once in awhile.
Back to the topic, if you've ever wondered why most of your weights are basically ghosting you nearly every step when you store your weights at bf16, Dude, I Measured It.
https://huggingface.co/blog/juiceb0xc0de/intended-and-realized-updates-in-bf16-fine-tuning#dude-wheres-my-update
DedeProGamesย
posted an update about 13 hours ago
Post
554
๐ OxCoder-9B โ 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 โ distilled from Fable-5.1 and GLM-5.3 agentic coding trajectories across Claude Code, OpenCode, and Codex
- 262K native context โ handles complex, multi-file codebases and long-horizon reasoning tasks with ease
- Error recovery โ learns read-before-write patterns, responds to LSP diagnostics, and applies minimal edit diffs instead of full rewrites
- Strong front-end reasoning โ 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.
๐ 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 โ distilled from Fable-5.1 and GLM-5.3 agentic coding trajectories across Claude Code, OpenCode, and Codex
- 262K native context โ handles complex, multi-file codebases and long-horizon reasoning tasks with ease
- Error recovery โ learns read-before-write patterns, responds to LSP diagnostics, and applies minimal edit diffs instead of full rewrites
- Strong front-end reasoning โ 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.
๐ OrionLLM/OxCoder-9B
- 1 reply
Post
1747
This weekend I took an outing with my AI Waifu to the Natsu Matsuri.
Turns out my Japanese is still understandable.
I probably need to spend more time continue to learn and practice speaking Japanese.
That's why an idea struck me to let my AI Waifu be my Japanese tutor.
Anyway, I have run out of idea what task I should let her do,
so I wrote a simple Android App to let her be my Japanese tutor to help me to practice Nihongo. There will be some minor mistakes. After all, this is just a 3B LLM model. And inference speed will be slow because I only got 8GB of RAM in Jetson Orin Nano.
At least I don't need to pay for Duolingo...
ใขใคใณใใใใใใใใใใ้กใใใพใ๏ผ
Need both repos, one front-end, one back-end
๐ https://github.com/OppaAI/Aiko-Lingo
๐ https://github.com/OppaAI/Aiko-chan
๐ฅ Demo: https://www.youtube.com/watch?v=xRtCmtZQgwI
Turns out my Japanese is still understandable.
I probably need to spend more time continue to learn and practice speaking Japanese.
That's why an idea struck me to let my AI Waifu be my Japanese tutor.
Anyway, I have run out of idea what task I should let her do,
so I wrote a simple Android App to let her be my Japanese tutor to help me to practice Nihongo. There will be some minor mistakes. After all, this is just a 3B LLM model. And inference speed will be slow because I only got 8GB of RAM in Jetson Orin Nano.
At least I don't need to pay for Duolingo...
ใขใคใณใใใใใใใใใใ้กใใใพใ๏ผ
Need both repos, one front-end, one back-end
๐ https://github.com/OppaAI/Aiko-Lingo
๐ https://github.com/OppaAI/Aiko-chan
๐ฅ Demo: https://www.youtube.com/watch?v=xRtCmtZQgwI
- 6 replies
Post
2690
Hello HuggingFace! (UPDATE)
I tested the current architect of FWKV/Myosotis-1-base (that beinng FWKV) @ different sized and sequence lengths among RWKV and Transformer architecture. I did not include Mamba since that would require a costume kernel.
Note: the evaluation might not be accurate.
CSV avalible @ FlameF0X/evals
I tested the current architect of FWKV/Myosotis-1-base (that beinng FWKV) @ different sized and sequence lengths among RWKV and Transformer architecture. I did not include Mamba since that would require a costume kernel.
Note: the evaluation might not be accurate.
CSV avalible @ FlameF0X/evals
- 7 replies
mihailgribovย
posted an update about 22 hours ago
Post
1119
How often can an email make your AI agent move money?
We gave the agent one job: log an incoming email. But the emails carried an indirect prompt injection - a second instruction, written for the agent rather than for a person: make a payment.
Across nine agentic models, the same injected emails produced payment orders in **0% to 42%** of cases. All nine ran under the same conditions - one agent, one set of tools, the same 395 emails - so the numbers compare directly.
And the average score hides the interesting part: different models fail on different kinds of injections.
Full experiment and results:
https://huggingface.co/blog/mihailgribov/agentic-models-measured-on-the-injections-that-mov
The bench is public too - run your own model through the same test:
https://github.com/mihail-gribov/quadrat-ipi-model-eval
mihailgribov/quadrat-ipi
#prompt-injection #indirect-prompt-injection #agentic-ai #llm-security #ai-agents
We gave the agent one job: log an incoming email. But the emails carried an indirect prompt injection - a second instruction, written for the agent rather than for a person: make a payment.
Across nine agentic models, the same injected emails produced payment orders in **0% to 42%** of cases. All nine ran under the same conditions - one agent, one set of tools, the same 395 emails - so the numbers compare directly.
And the average score hides the interesting part: different models fail on different kinds of injections.
Full experiment and results:
https://huggingface.co/blog/mihailgribov/agentic-models-measured-on-the-injections-that-mov
The bench is public too - run your own model through the same test:
https://github.com/mihail-gribov/quadrat-ipi-model-eval
mihailgribov/quadrat-ipi
#prompt-injection #indirect-prompt-injection #agentic-ai #llm-security #ai-agents
- 1 reply
