randomaidev_29147 thats me
🏗️ Building on HF
Boning Cui
Bc-AI
AI & ML interests
He/Him. I like LLM's and VLM's. I work with my other friends to make stuff. We are in year 7 and we are enthusiastic about AI. We are based in Australia 🇦🇺 (QLD Btw)
Recent Activity
new activity about 11 hours ago
Smilyai-labs/Nova-1-chat:hello? new activity about 13 hours ago
BananaMind/README:Aren't ArushCodes and Arush builds a part of bananamind? updated a model 1 day ago
Bc-AI/Sam-Checkpoint-TestOrganizations
replied to juiceb0xc0de's post 4 days ago
replied to juiceb0xc0de's post 4 days ago
@juiceb0xc0de can i add u?
replied to juiceb0xc0de's post 4 days ago
@juiceb0xc0de do u have discord
replied to Banaxi-Tech's post 4 days ago
@juiceb0xc0de Department of Model Interpretability DMI
replied to Banaxi-Tech's post 4 days ago
replied to Banaxi-Tech's post 4 days ago
@juiceb0xc0de do you want to join openmodel labs?
replied to Banaxi-Tech's post 4 days ago
is supra out?
replied to Banaxi-Tech's post 4 days ago
i will use them in my live voice chat model. Either supra or klein idk yet. mainly what voices i think is good
reacted to appvoid's post with ❤️ 4 days ago
Post
7,550
New leaderboard coming to the small language model community!
The leaderboard measures cognitive skills, which is more challenging and beyond language modeling and instruction-following. This is a first step towards more everyday useful and general small models.
dotlabs/cognirank
The leaderboard measures cognitive skills, which is more challenging and beyond language modeling and instruction-following. This is a first step towards more everyday useful and general small models.
dotlabs/cognirank
- 2 replies
reacted to Banaxi-Tech's post with 🚀🔥 5 days ago
Post
4,235
we're releasing Klein TTS X1.5 at klein-ml
it has a flash lite at 0.4m, flash at 1,7m and pro at 13m. they score near 82m models at very low sizes.
there supposed to be able to be bundled with any app without adding bloat.
we're going to release x1.6 soon a preview of our x2 architecture.
klein-ml/Klein-TTS-X1.5-Flash-Lite
klein-ml/Klein-TTS-X1.5-Flash
klein-ml/Klein-TTS-X1.5-Pro
it has a flash lite at 0.4m, flash at 1,7m and pro at 13m. they score near 82m models at very low sizes.
there supposed to be able to be bundled with any app without adding bloat.
we're going to release x1.6 soon a preview of our x2 architecture.
klein-ml/Klein-TTS-X1.5-Flash-Lite
klein-ml/Klein-TTS-X1.5-Flash
klein-ml/Klein-TTS-X1.5-Pro
- 4 replies
reacted to kutomanovhennadii's post with 🔥 5 days ago
Post
4,719
How much load can a language model handle?
“Summarize a Wikipedia article in at least 300 words. Use no commas. Split your answer into three titled sections.”
This is the kind of task used in IFEval, a benchmark of how well models follow multiple requirements at once.
Suppose the model breaks one requirement. Did it lose track of an instruction? Did the no-comma rule make the summary harder to write? Or was summarizing the article difficult to begin with? A program can tell us what failed, but not separate instruction load from task difficulty and interacting constraints.
There is another approach: synthetic tests where a model retrieves a key's value from a long list. Those are easier to control, but they test information retrieval rather than the execution of multiple instructions.
So how can we measure the load itself?
That's the question behind my new article on the IEC instrument. Instead of an essay, the model gets meaningless text made of random words. Instead of complex constraints, it gets simple replacement rules such as
The simplicity serves a purpose. Each rule applies to its own word, so we can add instructions without changing the operation. We can also set how many different words the text has and how often each repeats. And every application has a known correct outcome.
A single response thus produces many individually verifiable trials, not just one overall score. This lets us study how a model's behavior degrades under different kinds of load.
The article walks through the instrument, an actual prompt and GPT-4o mini response, and how to reproduce the trials. Code and data are public.
Article: https://huggingface.co/blog/kutomanovhennadii/how-to-measure-a-language-models-behavior-under-lo
Data: kutomanovhennadii/iec-gpt-4o-mini-2024-07-18
Originally written in Russian. English translation assisted by AI.
“Summarize a Wikipedia article in at least 300 words. Use no commas. Split your answer into three titled sections.”
This is the kind of task used in IFEval, a benchmark of how well models follow multiple requirements at once.
Suppose the model breaks one requirement. Did it lose track of an instruction? Did the no-comma rule make the summary harder to write? Or was summarizing the article difficult to begin with? A program can tell us what failed, but not separate instruction load from task difficulty and interacting constraints.
There is another approach: synthetic tests where a model retrieves a key's value from a long list. Those are easier to control, but they test information retrieval rather than the execution of multiple instructions.
So how can we measure the load itself?
That's the question behind my new article on the IEC instrument. Instead of an essay, the model gets meaningless text made of random words. Instead of complex constraints, it gets simple replacement rules such as
lake -> stone. Its job is to rewrite the text while applying every rule.The simplicity serves a purpose. Each rule applies to its own word, so we can add instructions without changing the operation. We can also set how many different words the text has and how often each repeats. And every application has a known correct outcome.
A single response thus produces many individually verifiable trials, not just one overall score. This lets us study how a model's behavior degrades under different kinds of load.
The article walks through the instrument, an actual prompt and GPT-4o mini response, and how to reproduce the trials. Code and data are public.
Article: https://huggingface.co/blog/kutomanovhennadii/how-to-measure-a-language-models-behavior-under-lo
Data: kutomanovhennadii/iec-gpt-4o-mini-2024-07-18
Originally written in Russian. English translation assisted by AI.
- 2 replies
reacted to iliya-radulov's post with 🔥 5 days ago
Post
4,448
Field Notes from a Low-Cost Robot Learning Lab: Hardware Churn, Software Whiplash, and What Actually Went Wrong
An informal companion piece documenting the hardware incidents, framework churn, and debugging dead-ends from roughly seven weeks of work. It is written for people building similar setups on a hobbyist budget and is candid about the time lost to causes like loose power cables and swapped ports.
Zenodo: https://zenodo.org/records/23259698
About me: I am an independent researcher. These works are part of a single-operator project on low-cost robot learning. My ORCID is 0000-0001-8943-5083. For questions or collaboration, feel free to reach out via the HF community.
An informal companion piece documenting the hardware incidents, framework churn, and debugging dead-ends from roughly seven weeks of work. It is written for people building similar setups on a hobbyist budget and is candid about the time lost to causes like loose power cables and swapped ports.
Zenodo: https://zenodo.org/records/23259698
About me: I am an independent researcher. These works are part of a single-operator project on low-cost robot learning. My ORCID is 0000-0001-8943-5083. For questions or collaboration, feel free to reach out via the HF community.
replied to Banaxi-Tech's post 6 days ago
@Banaxi-Tech How would I message you? Also @Bc-AI and @ArushCodes
uh you can use my bc@kleinml.com email.
replied to Banaxi-Tech's post 6 days ago
@Banaxi-Tech have a look here
replied to SeaWolf-AI's post 6 days ago
nice!
reacted to SeaWolf-AI's post with 🧠😎👍👀 6 days ago
Post
4,592
No GPU. No cloud. Just your phone.
Most “small” models still beg for a datacenter. Ours fit in your pocket.
VIDRAFT POCKET is a family of GGUF models that run on an iPhone and on a GPU-free PC, straight out of the box with llama.cpp, Ollama, LM Studio, and PocketPal. Seven weeks after launch they crossed 1 million downloads. Today the family is past 2.81 million and still climbing, every day.
Three models, one pocket:
🟢 POCKET-35B — a 35B mixture-of-experts that runs on an iPhone and on a PC with no GPU. Balanced power.
→ FINAL-Bench/POCKET-35B-GGUF
🔵 POCKET-26B — a Gemma-4 based 26B MoE, tuned for on-device Korean. Lightweight and fast.
→ FINAL-Bench/POCKET-26B-GGUF
🟣 POCKET-Darwin-180B — a 180B flagship running on a laptop in 4-bit GGUF. The datacenter, on your desk.
→ FINAL-Bench/POCKET-Darwin-180B-GGUF
The whole family lives here:
FINAL-Bench
Try our models live in the browser: FINAL-Bench/POCKET-Image-Studio
Private by default. Offline by design. Yours to run.
#OnDeviceAI #LocalLLM #llamacpp #GGUF #VIDRAFT #POCKET
Most “small” models still beg for a datacenter. Ours fit in your pocket.
VIDRAFT POCKET is a family of GGUF models that run on an iPhone and on a GPU-free PC, straight out of the box with llama.cpp, Ollama, LM Studio, and PocketPal. Seven weeks after launch they crossed 1 million downloads. Today the family is past 2.81 million and still climbing, every day.
Three models, one pocket:
🟢 POCKET-35B — a 35B mixture-of-experts that runs on an iPhone and on a PC with no GPU. Balanced power.
→ FINAL-Bench/POCKET-35B-GGUF
🔵 POCKET-26B — a Gemma-4 based 26B MoE, tuned for on-device Korean. Lightweight and fast.
→ FINAL-Bench/POCKET-26B-GGUF
🟣 POCKET-Darwin-180B — a 180B flagship running on a laptop in 4-bit GGUF. The datacenter, on your desk.
→ FINAL-Bench/POCKET-Darwin-180B-GGUF
The whole family lives here:
Try our models live in the browser: FINAL-Bench/POCKET-Image-Studio
Private by default. Offline by design. Yours to run.
#OnDeviceAI #LocalLLM #llamacpp #GGUF #VIDRAFT #POCKET
- 3 replies