brittlewis12
responses api, by contrast, is stateful — only send the latest message, and openai stores the conversation history, while keeping track of other details on behalf of the calling app, like parallel tool call states.
but i would say that since chat completions has become an informal industry standard, the responses api feels like an attempt by openai to break away from that shared interface, because it is so easy to swap out providers with nothing more than a base url and a model id, to a paradigm which requires data migration as well as replacement infrastructure (containers for code execution, for example).
``` { "telemetry": { "diagnostics": false, "metrics": false } } ```
for anyone who wants a fast, modern, resource-minimal, gpu-native text editor that is open source.
I’ve just submitted a new update for review with a number of small but material changes to address these issues: https://news.ycombinator.com/item?id=38920916
I hope you’ll consider giving it another shot once that’s live, and thank you for taking the time not just to test but also to report your experience!
Britt
I’ve just submitted a new update for review with a few small but hopefully noticeable changes, thanks to your feedback:
1. StableLM Zephyr 3b Q4_K_M is now the built-in model, replacing the Q6_K variant.
2. More aggressive RAM headroom calculation, with forced fallback to CPU rather than failing to load or crashing/hanging in such a nasty fashion.
3. New status indicator for Metal when model is loaded (filled bolt for enabled, vs slashed bolt for disabled.)
4. Metal will now also be enabled for devices with 4GB RAM or less, but only when the selected model can comfortably fit in RAM. Previously, only devices with at least 6GB ever had Metal enabled.
I really appreciate your taking the time to test — the hanging you experienced was unacceptable, and I truly am sorry for the inconvenience. I hope you’ll give it another chance once this update is live, but either way I’m grateful for your help in isolating and eliminating this issue!
Britt
I’ve just submitted a new update for review with a few small but hopefully noticeable changes, thanks in no small part to your feedback:
1. StableLM Zephyr 3b Q4_K_M is now the built-in model, replacing the Q6_K variant.
2. More aggressive RAM headroom calculation, with forced fallback to CPU rather than failing to load as you observed, or crashing outright in some nasty edge cases.
3. New status indicator for Metal when model is loaded (filled bolt for enabled, vs slashed bolt for disabled.)
4. Metal will now also be enabled for devices with 4GB RAM or less, but only when the selected model can comfortably fit in RAM. Previously, only devices with at least 6GB had Metal enabled.
Thank you so much for taking the time to test and share your experience! Feel free to reach out anytime at britt [at] bl3 [dot] dev.
Britt
1. StableLM Zephyr 3b Q4_K_M is now the built-in model, replacing the Q6_K variant.
2. More aggressive RAM headroom calculation, with forced fallback to CPU rather than failing to load or crashing.
3. New status indicator for Metal when model is loaded (filled bolt for enabled, vs slashed bolt for disabled.)
4. Metal will now also be enabled for devices with 4GB RAM or less, but only when the selected model can comfortably fit in RAM. Previously, only devices with at least 6GB had Metal enabled.
Thank you so much again for your time!
It’s still early days, but at a high level, I have a few goals: - expand accessibility and increase awareness of the power & viability of small models — the scene can be quite impenetrable for many! - provide the an easy to use, attractive, efficient app that’s a good platform citizen, taking full advantage of Apple’s powerful device capabilities; - empower more people to protect their private conversation data, which has material value to large AI companies; - incentivize more experimentation, training & fine-tuning efforts focused on small, privately-runnable models.
I’d love to one day become your habitual ChatGPT alternative, as high a bar as that may be.
I have some exciting ideas, from enabling a user generated public gallery of characters; to expanding into multimodal use cases, like images & speech; composing larger workflows on top of LLMs, similar to Shortcuts; grounding open models against web search indices for factuality; and further out, more speculative ideas, including exposing tools like JavaScriptCore to models as a tool, like Python in ChatGPT’s code interpreter.
But I’m sure you’ve also given a lot of thought to the future of AI on device with smol — what are some dreams you have for truly private AI that’s always with you?
Britt
Practically, a few things:
If you want to have your cake & eat it too, they recommend Enumerated Shapes[1] in their coremltools docs, where CoreML precompiles up to 128 (!) variants of input shapes, but again this is fairly limiting (1 tok, 2 tok, 3 tok... up to 128 token prompts.. maybe you enforce a minimum, say 80 tokens to account for a system prompt, so up to 200 tokens, but... still pretty short). But this is only compatible with CPU inference, so that reduces its appeal.
It seems like its current state was designed for text embedding models, where you normalize input length by chunking (often 128 or 256 tokens) and operate on the chunks — and indeed, that’s the only text-based CoreML model that Apple ships today, a Bert embedding model tuned for Q&A[2], not an LLM.
You could used a fixed input length that’s fairly large; I haven’t experimented with it once I grasped the memory requirements, but from what I gather from HuggingFace’s announcement blog post[3], it seems that is what they do with swift-transformers & their CoreML conversions, handling the details for you[4][5]. I haven’t carefully investigated the implementation, but I’m curious to learn more!
You can be sure that no one is more aware of all this than Apple — they published "Deploying Transformers on the Apple Neural Engine" in June 2022[6]. I look forward to seeing what they cook up for developers at WWDC this year!
---
[1] "Use `EnumeratedShapes` for best performance. During compilation the model can be optimized on the device for the finite set of input shapes. You can provide up to 128 different shapes." https://apple.github.io/coremltools/docs-guides/source/flexi...
[2] BertSQUAD.mlmodel (fp16) https://developer.apple.com/machine-learning/models/#text
[3] https://huggingface.co/blog/swift-coreml-llm#optimization
[4] `use_fixed_shapes` "Retrieve the max sequence length from the model configuration, or use a hardcoded value (currently 128). This can be subclassed to support custom lengths." https://github.com/huggingface/exporters/pull/37/files#diff-...
[5] `use_flexible_shapes` "When True, inputs are allowed to use sequence lengths of `1` up to `maxSequenceLength`. Unfortunately, this currently prevents the model from running on GPU or the Neural Engine. We default to `False`, but this can be overridden in custom configurations." https://github.com/huggingface/exporters/pull/37/files#diff-...
[6] https://machinelearning.apple.com/research/neural-engine-tra...
My understanding is Metal is currently causing hangs on devices when there is barely enough RAM to fit the model and prompt, but not quite enough to run. Will work on falling back to CPU to avoid this kind of experience much more aggressively than today.
Thank you for taking the time to both try it out and to share your experience; I will use it to ensure it’s better in the future.
Thrilled about all those developments! More model options as well as link-based GGUF downloads on the way.
On the 7b models: I’m very sorry for the poor experience. I wouldn’t recommend 7b over Q2_K at the moment, unless you’re on a 16GB iPad (or an Apple Silicon Mac!). This needs to be much clearer, as you observed the consequences can be severe. The larger models, and even 3b Q6_K can be crash prone due to memory pressure. Will work on improve handling of low level out-of-memory errors very soon.
Will also investigate the StableLM crashes, I’m sorry about that! Hopefully Testflight recorded a trace. Just speculating, it may be a similar issue to the larger models, due to the higher-fidelity quant (Q6_K) combined with the context length eventually running out of RAM. Could you give the Q4_K_M a shot? I heard something similar from a friend yesterday, I’m curious if you have a better time with that — perhaps that’s a more sensible default.
Re: the overly-protective new chat alert, I agree, thanks for the suggestion. I’ll incorporate that into the next build. Can I credit you? Let me know how you’d like for me to refer to you, and I’d be happy to.
Finally, please feel free to email me any further feedback, and thanks again for your time and consideration!
britt [at] bl3 [dot] dev
Why? I suggest a few main reasons: 1) No Neural Engine API 2) CoreML has challenges modeling LLMs efficiently right now. 3) Not Enough Benefit (For the Cost... Yet!)
This is my best understanding based on my own work and research for a local LLM iOS app. Read on for more in-depth justifications of each point!
---
1) No Neural Engine API
- There is no developer API to use the Neural Engine programmatically, so CoreML is the only way to be able to use it.
2) CoreML has challenges modeling LLMs efficiently right now.
- Its most-optimized use cases seem tailored for image models, as it works best with fixed input lengths[1][2], which are fairly limiting for general language modeling (are all prompts, sentences and paragraphs, the same number of tokens? do you want to pad all your inputs?).
- CoreML features limited support for the leading approaches for compressing LLMs (quantization, whether weights-only or activation-aware). Falcon-7b-instruct (fp32) in CoreML is 27.7GB [3], Llama-2-chat (fp16) is 13.5GB [4] — neither will fit in memory on any currently shipping iPhone. They'd only barely fit on the newest, highest-end iPad Pros.
- HuggingFace‘s swift-transformers[5] is a CoreML-focused library under active development to eventually help developers with many of these problems, in addition to an `exporters` cli tool[6] that wraps Apple's `coremltools` for converting PyTorch or other models to CoreML.
3) Not Enough Benefit (For the Cost... Yet!)
- ANE & GPU (Metal) have access to the same unified memory. They are both subject to the same restrictions on background execution (you simply can't use them in the background, or your app is killed[7]).
- So the main benefit from unlocking the ANE would be multitasking: running an ML task in parallel with non-ML tasks that might also require the GPU: e.g. SwiftUI Metal Shaders, background audio processing (shoutout Overcast!), screen recording/sharing, etc. Absolutely worthwhile to achieve, but for the significant work required and the lack of ecosystem currently around CoreML for LLMs specifically, the benefits become less clear.
- Apple's hot new ML library, MLX, only uses Metal for GPU[8], just like Llama.cpp. More nuanced differences arise on closer inspection related to MLX's focus on unified memory optimizations. So perhaps we can squeeze out some performance from unified memory in Llama.cpp, but CoreML will be the only way to unlock ANE, which is lower priority according to lead maintainer Georgi Gerganov as of late this past summer[9], likely for many of the reasons enumerated above.
I've learned most of this while working on my own private LLM inference app, cnvrs[10] — would love to hear your feedback or thoughts!
Britt
---
[1] https://github.com/huggingface/exporters/pull/37
[2] https://apple.github.io/coremltools/docs-guides/source/flexi...
[3] https://huggingface.co/tiiuae/falcon-7b-instruct/tree/main/c...
[4] https://huggingface.co/coreml-projects/Llama-2-7b-chat-corem...
[5] https://github.com/huggingface/swift-transformers
[6] https://github.com/huggingface/exporters
[7] https://developer.apple.com/documentation/metal/gpu_devices_...
[8] https://github.com/ml-explore/mlx/issues/18
[9] https://github.com/ggerganov/llama.cpp/issues/1714#issuecomm...
would love to hear what you think: https://testflight.apple.com/join/ERFxInZg
- save characters (system prompt + temperature, and a name & cosmetic color) - download & experiment with models from 1b, 3b, & 7b, and quant options q2k, q4km, q6k - save, search, continue, & export past chats
along with smaller touches: - custom theme colors - haptics
and more coming soon!