As a regular user of a bunch of specialized micromodels, I'll tell you this: you won't be happy with such a model (and its JEV counterparts) running permanently in the background on your PC's CPU. You need to offload their processing to the NPU. There are many pitfalls along the way, but the result is worth it.
NPU performance will be twice as high, while power consumption will be four times lower. No additional fan noise (if you know what I mean).
I'll wait another month until the first phase of the =battle royale= among models of this kind wraps up, put together a solution for the NPU/iGPU, and post it on HF.
Does anyone know if it is worth fine-tuning one of these decision models on the shape of the questions you want it to work on, vs the more general versions? I'm using Jev pretty successfully at work at the moment, but am curious about what is doable
The new OpenAI Decisions API calls it "predicate". Also calling the API "decisions" rather than "system one". Usually I don't like inventing new standards but I hope the OpenAI schema takes over. We don't need this hype terminology.
Can someone explain this architecture a bit more in depth? They say the pointer head scores the hidden state at each option against the hidden state of the answer. But the LLM produces hidden states per token, so an option can span multiple tokens, no?
The ~2-week-old Intern-Decision family of models (0.8B, 2B and 4B) have the same Qwen3.5 base model family (albeit the instruction-tuned variants) and pointer head architecture.
Are any of these multimodal yet? I'd love to try asking a model with calibrated probabilities to answer question like, "do these shapes match?". Sure, you can ask a LLM....
clef from cloudflare runs on llama.cpp - being locked-in to strands cli would be a bummer and will slow down adoption.
Since it's a LoRa on Qwen, I assume this is runnable via llama.cpp. Pity that the PEFT/LoRa->GGUF translation is left to the user. Anyone got past:
$ uv run --with transformers==5.19.0 convert_lora_to_gguf.py ~/Downloads/lora --dry-run --verbose
[...]
File "/Users/user/repos/llama.cpp/conversion/base.py", line 630, in map_tensor_name
raise ValueError(f"Can not map tensor {name!r}")
ValueError: Can not map tensor 'layers.0.linear_attn.in_proj_a.weight'
As a regular user of a bunch of specialized micromodels, I'll tell you this: you won't be happy with such a model (and its JEV counterparts) running permanently in the background on your PC's CPU. You need to offload their processing to the NPU. There are many pitfalls along the way, but the result is worth it.
NPU performance will be twice as high, while power consumption will be four times lower. No additional fan noise (if you know what I mean).
I'll wait another month until the first phase of the =battle royale= among models of this kind wraps up, put together a solution for the NPU/iGPU, and post it on HF.
Does anyone know if it is worth fine-tuning one of these decision models on the shape of the questions you want it to work on, vs the more general versions? I'm using Jev pretty successfully at work at the moment, but am curious about what is doable
At this point I can't wait for a comedian to release a decision model backed by humans.
Meet Jerry- it's literally a guy named Jerry answering your questions.
Your comment made me chuckle.
Jerry, "The Decider" https://www.youtube.com/watch?v=r8VbzrZ9yHQ
Same, but my mind went straight to Rick and Morty… def don’t want Jerry deciding XD
Oh! You probably want ChatTJB [1]
[1] - https://chattjb.org/about
Don't worry, Jerry will rig everything up for you.
RACE HIM JERRY!
Why is everyone calling binary choices `noul`? Does this have some meaning or is it just copying Jev’s API?
It's from Bernoulli.
Interesting. Is that a unit he invented or is it just a reference to his last name that stuck?
From Bernoulli maps apparently. I still don't understand why[0].
[0] https://news.ycombinator.com/item?id=49723267 (see parent for reference)
The new OpenAI Decisions API calls it "predicate". Also calling the API "decisions" rather than "system one". Usually I don't like inventing new standards but I hope the OpenAI schema takes over. We don't need this hype terminology.
Claude generated it and it stuck.
The same reason why they’re calling this System One thinking. Everyone wants to be seen doing different things and smart ones.
Can someone explain this architecture a bit more in depth? They say the pointer head scores the hidden state at each option against the hidden state of the answer. But the LLM produces hidden states per token, so an option can span multiple tokens, no?
The ~2-week-old Intern-Decision family of models (0.8B, 2B and 4B) have the same Qwen3.5 base model family (albeit the instruction-tuned variants) and pointer head architecture.
https://huggingface.co/collections/internlm/intern-decision
Fantastically well written. It's rare for me to be able to understand what the AI gurus are talking about, and this was written by humans for humans.
It can technically be used for a lot of use cases, I'd like people to chime in on ideas on this?
Picking lunch menu..?
Are any of these multimodal yet? I'd love to try asking a model with calibrated probabilities to answer question like, "do these shapes match?". Sure, you can ask a LLM....
Cloudflare’s clef is multimodal (https://blog.cloudflare.com/clef-decision-models/)
(Disclaimer, I work at Cloudflare, but not on models)
Strands Decider can take vision in. How does it go with that question?
This is not advertised on their page, did you make this up?
I believe image classification/analysis by deciders (not just OCR, not everything is about text) is still lacking.
Cloudflare's Clef had fair results on my test, but it's larger and slower. Wondering about Strands.
clef from cloudflare runs on llama.cpp - being locked-in to strands cli would be a bummer and will slow down adoption.
Since it's a LoRa on Qwen, I assume this is runnable via llama.cpp. Pity that the PEFT/LoRa->GGUF translation is left to the user. Anyone got past:
This is a great model. I've been running it on device in chrome extension to filter things like email.
It is just the right mix of size, capability and speed to make it generally useful for adhoc bulk classification tasks.
For those wanting to run it in browser: https://huggingface.co/alxnahas/strands-decider-2B-webgpu
Live demo: https://alxnahas.github.io/strands-decider-web/?backend=engi...
Benchmark calibration does not establish reliability on unfamiliar production inputs.
Any idea how well this would run on a CPU?
On my M3 mac, it works okay inside a docker container with just CPU.
{ "model": "strands-decider-2B-hobson-v19", "answers": { "is_urgent": { "type": "noul", "noul": 0.8287 } }, "usage": { "input_tokens": 86, "output_tokens": 1 }, "latency_ms": 1732.17 }
This is how I got it running - https://gist.github.com/2891eb0db9ea92c1a4e860d44f556292
There's a lot more to be done if we optimize for MLX & let it run on a Mac mini instead of the docker wrapper.
About half a second per decision on six cores
Isnt that a bit slow for these?
2B being called small is such a sign of the times
Looks really nice, I think I could use it on my Mac mini for some smaller automations
a strand type game