Wow this is super cool! Thanks for sharing!
Tyler Williams PRO
unmodeled-tyler
AI & ML interests
Founder of Quanta Intellect/VANTA Research - Looking to get in touch? Head to my website!
Recent Activity
replied to
fabiosuizu's
post
about 16 hours ago
Hi everyone!
I've been working on a pronunciation assessment engine optimized for edge deployment and real-time feedback. Wanted to share it with the community and get feedback.
**What it does**: Scores English pronunciation at 4 levels of granularity — phoneme, word, sentence, and overall (0-100 each). Returns IPA and ARPAbet notation for every phoneme.
**Key specs**:
- 17MB total model size (NeMo Citrinet-256, INT4 quantized)
- 257ms median inference on CPU
- Exceeds human inter-annotator agreement at phone-level (+4.5%) and sentence-level (+5.2%)
- Benchmarked on speechocean762 (2,500 test utterances)
- Tested across 7 L1 backgrounds (Chinese, Japanese, Korean, Arabic, Spanish, Vietnamese, Russian)
**Architecture**: CTC forced alignment + Viterbi decoding + GOP (Goodness of Pronunciation) scoring + MLP/XGBoost ensemble heads. No wav2vec2 dependency — the entire pipeline runs in 17MB.
**Try it**: https://huggingface.co/spaces/fabiosuizu/pronunciation-assessment
The demo lets you record audio or upload a file, enter the expected text, and get instant scoring down to individual phonemes.
**API access**: Available via REST API, MCP servers (for AI agents), and Azure Marketplace. Details in the Space description.
Would love feedback on:
1. Use cases you'd find this useful for
2. Languages you'd want supported next
3. Whether the scoring feels calibrated for your experience level
Thanks!
reacted
to
fabiosuizu's
post
with 🔥
about 16 hours ago
Hi everyone!
I've been working on a pronunciation assessment engine optimized for edge deployment and real-time feedback. Wanted to share it with the community and get feedback.
**What it does**: Scores English pronunciation at 4 levels of granularity — phoneme, word, sentence, and overall (0-100 each). Returns IPA and ARPAbet notation for every phoneme.
**Key specs**:
- 17MB total model size (NeMo Citrinet-256, INT4 quantized)
- 257ms median inference on CPU
- Exceeds human inter-annotator agreement at phone-level (+4.5%) and sentence-level (+5.2%)
- Benchmarked on speechocean762 (2,500 test utterances)
- Tested across 7 L1 backgrounds (Chinese, Japanese, Korean, Arabic, Spanish, Vietnamese, Russian)
**Architecture**: CTC forced alignment + Viterbi decoding + GOP (Goodness of Pronunciation) scoring + MLP/XGBoost ensemble heads. No wav2vec2 dependency — the entire pipeline runs in 17MB.
**Try it**: https://huggingface.co/spaces/fabiosuizu/pronunciation-assessment
The demo lets you record audio or upload a file, enter the expected text, and get instant scoring down to individual phonemes.
**API access**: Available via REST API, MCP servers (for AI agents), and Azure Marketplace. Details in the Space description.
Would love feedback on:
1. Use cases you'd find this useful for
2. Languages you'd want supported next
3. Whether the scoring feels calibrated for your experience level
Thanks!
reacted
to
MonsterMMORPG's
post
with 👀
about 16 hours ago
SECourses Ultimate Video and Image Upscaler Pro is now V2.1 and massive improvements has arrived
Check all below screenshots to see all amazing features
20 Feburary 2026 Update V2.1
This is a pretty big update
We have 100% changed the FlashVSR+ backend to a new repo and I have significantly upgraded this repo
The new FlashVSR+ works amazing and I think it is better than SeedVR2 for high res videos upscale like upscaling 720p into higher resolution
Top menu navigation bar updated into a better version and view
FlashVSR+ tab remade and all the features are now working
For lower VRAM a button is added which you can use if you get OOM
Read the updated UI to understand how to use
FlashVSR+ now can upscale images very well as well
Image Based GAN upscalers tab also improved and some bugs fixed
Output & Comparison tab Video Output was not working properly and this issue fix fixed
In Output & Comparison tab, new multi video and multi image comparison sliders added which is super useful to quickly compare multiple videos and images
Lots of various bug fixes made
App is getting closer to be perfect please heavily test it and let me know errors and what features you request
This update was mostly about improving the FlashVSR+ since it is a very fast and amazing video upscaler model
Image Based - Gan upscale now can upscale videos perfectly fine and Batch Size (Frames per Iteration) is now working to speed up upscaling videos
For updating, get the latest zip file, extract and overwrite all files and run Windows_Run_SECourses_Upscaler_Pro.bat file
Organizations
replied to
fabiosuizu's
post
about 16 hours ago
reacted to
fabiosuizu's
post with 🔥
about 16 hours ago
Post
688
Hi everyone!
I've been working on a pronunciation assessment engine optimized for edge deployment and real-time feedback. Wanted to share it with the community and get feedback.
**What it does**: Scores English pronunciation at 4 levels of granularity — phoneme, word, sentence, and overall (0-100 each). Returns IPA and ARPAbet notation for every phoneme.
**Key specs**:
- 17MB total model size (NeMo Citrinet-256, INT4 quantized)
- 257ms median inference on CPU
- Exceeds human inter-annotator agreement at phone-level (+4.5%) and sentence-level (+5.2%)
- Benchmarked on speechocean762 (2,500 test utterances)
- Tested across 7 L1 backgrounds (Chinese, Japanese, Korean, Arabic, Spanish, Vietnamese, Russian)
**Architecture**: CTC forced alignment + Viterbi decoding + GOP (Goodness of Pronunciation) scoring + MLP/XGBoost ensemble heads. No wav2vec2 dependency — the entire pipeline runs in 17MB.
**Try it**: fabiosuizu/pronunciation-assessment
The demo lets you record audio or upload a file, enter the expected text, and get instant scoring down to individual phonemes.
**API access**: Available via REST API, MCP servers (for AI agents), and Azure Marketplace. Details in the Space description.
Would love feedback on:
1. Use cases you'd find this useful for
2. Languages you'd want supported next
3. Whether the scoring feels calibrated for your experience level
Thanks!
I've been working on a pronunciation assessment engine optimized for edge deployment and real-time feedback. Wanted to share it with the community and get feedback.
**What it does**: Scores English pronunciation at 4 levels of granularity — phoneme, word, sentence, and overall (0-100 each). Returns IPA and ARPAbet notation for every phoneme.
**Key specs**:
- 17MB total model size (NeMo Citrinet-256, INT4 quantized)
- 257ms median inference on CPU
- Exceeds human inter-annotator agreement at phone-level (+4.5%) and sentence-level (+5.2%)
- Benchmarked on speechocean762 (2,500 test utterances)
- Tested across 7 L1 backgrounds (Chinese, Japanese, Korean, Arabic, Spanish, Vietnamese, Russian)
**Architecture**: CTC forced alignment + Viterbi decoding + GOP (Goodness of Pronunciation) scoring + MLP/XGBoost ensemble heads. No wav2vec2 dependency — the entire pipeline runs in 17MB.
**Try it**: fabiosuizu/pronunciation-assessment
The demo lets you record audio or upload a file, enter the expected text, and get instant scoring down to individual phonemes.
**API access**: Available via REST API, MCP servers (for AI agents), and Azure Marketplace. Details in the Space description.
Would love feedback on:
1. Use cases you'd find this useful for
2. Languages you'd want supported next
3. Whether the scoring feels calibrated for your experience level
Thanks!
-
- 1 reply
reacted to
MonsterMMORPG's
post with 👀
about 16 hours ago
Post
1236
SECourses Ultimate Video and Image Upscaler Pro is now V2.1 and massive improvements has arrived
Check all below screenshots to see all amazing features
20 Feburary 2026 Update V2.1
This is a pretty big update
We have 100% changed the FlashVSR+ backend to a new repo and I have significantly upgraded this repo
The new FlashVSR+ works amazing and I think it is better than SeedVR2 for high res videos upscale like upscaling 720p into higher resolution
Top menu navigation bar updated into a better version and view
FlashVSR+ tab remade and all the features are now working
For lower VRAM a button is added which you can use if you get OOM
Read the updated UI to understand how to use
FlashVSR+ now can upscale images very well as well
Image Based GAN upscalers tab also improved and some bugs fixed
Output & Comparison tab Video Output was not working properly and this issue fix fixed
In Output & Comparison tab, new multi video and multi image comparison sliders added which is super useful to quickly compare multiple videos and images
Lots of various bug fixes made
App is getting closer to be perfect please heavily test it and let me know errors and what features you request
This update was mostly about improving the FlashVSR+ since it is a very fast and amazing video upscaler model
Image Based - Gan upscale now can upscale videos perfectly fine and Batch Size (Frames per Iteration) is now working to speed up upscaling videos
For updating, get the latest zip file, extract and overwrite all files and run Windows_Run_SECourses_Upscaler_Pro.bat file
Check all below screenshots to see all amazing features
20 Feburary 2026 Update V2.1
This is a pretty big update
We have 100% changed the FlashVSR+ backend to a new repo and I have significantly upgraded this repo
The new FlashVSR+ works amazing and I think it is better than SeedVR2 for high res videos upscale like upscaling 720p into higher resolution
Top menu navigation bar updated into a better version and view
FlashVSR+ tab remade and all the features are now working
For lower VRAM a button is added which you can use if you get OOM
Read the updated UI to understand how to use
FlashVSR+ now can upscale images very well as well
Image Based GAN upscalers tab also improved and some bugs fixed
Output & Comparison tab Video Output was not working properly and this issue fix fixed
In Output & Comparison tab, new multi video and multi image comparison sliders added which is super useful to quickly compare multiple videos and images
Lots of various bug fixes made
App is getting closer to be perfect please heavily test it and let me know errors and what features you request
This update was mostly about improving the FlashVSR+ since it is a very fast and amazing video upscaler model
Image Based - Gan upscale now can upscale videos perfectly fine and Batch Size (Frames per Iteration) is now working to speed up upscaling videos
For updating, get the latest zip file, extract and overwrite all files and run Windows_Run_SECourses_Upscaler_Pro.bat file
- 1 reply
reacted to
their
post with 🚀
1 day ago
Post
1254
New Article: https://huggingface.co/blog/unmodeled-tyler/how-we-learned-to-talk-to-machines
I was inspired by a single word in a Mac terminal prompt recently; "we."
The result is a bit of a journey through computational culture and history where we explore collaborative software design from the earliest computing systems to modern day AI systems.
I discuss how Large Language Models and collaborative AI interaction as we experience it today are a natural evolution in a long lineage of tools that came before; each compounding on last.
From CLI tools in the 60s-70s, to Clippy, to ChatGPT. I trace the history of "machines with a voice." Check it out!
I was inspired by a single word in a Mac terminal prompt recently; "we."
The result is a bit of a journey through computational culture and history where we explore collaborative software design from the earliest computing systems to modern day AI systems.
I discuss how Large Language Models and collaborative AI interaction as we experience it today are a natural evolution in a long lineage of tools that came before; each compounding on last.
From CLI tools in the 60s-70s, to Clippy, to ChatGPT. I trace the history of "machines with a voice." Check it out!
posted
an
update
1 day ago
Post
1254
New Article: https://huggingface.co/blog/unmodeled-tyler/how-we-learned-to-talk-to-machines
I was inspired by a single word in a Mac terminal prompt recently; "we."
The result is a bit of a journey through computational culture and history where we explore collaborative software design from the earliest computing systems to modern day AI systems.
I discuss how Large Language Models and collaborative AI interaction as we experience it today are a natural evolution in a long lineage of tools that came before; each compounding on last.
From CLI tools in the 60s-70s, to Clippy, to ChatGPT. I trace the history of "machines with a voice." Check it out!
I was inspired by a single word in a Mac terminal prompt recently; "we."
The result is a bit of a journey through computational culture and history where we explore collaborative software design from the earliest computing systems to modern day AI systems.
I discuss how Large Language Models and collaborative AI interaction as we experience it today are a natural evolution in a long lineage of tools that came before; each compounding on last.
From CLI tools in the 60s-70s, to Clippy, to ChatGPT. I trace the history of "machines with a voice." Check it out!
reacted to
qgallouedec's
post with 🔥
1 day ago
Post
2004
@CohereLabs
just released 🌿 Tiny Aya: a fully open-source 3B parameter model that speaks 70+ languages 🌍! But there’s a catch:
Tiny Aya is just a language model. It doesn’t support tool calling, the key capability that turns frontier models into powerful *agents*.
So the real question is:
How hard is it to turn Tiny Aya into an agent?
Turns out… it’s simple, thanks to Hugging Face TRL.
We’re sharing a hands-on example showing how to train Tiny Aya to turn it into a tool-calling agent using TRL, unlocking what could become the first *massively multilingual open agent*.
Small model. Global reach. Agent capabilities.
👉 https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
Tiny Aya is just a language model. It doesn’t support tool calling, the key capability that turns frontier models into powerful *agents*.
So the real question is:
How hard is it to turn Tiny Aya into an agent?
Turns out… it’s simple, thanks to Hugging Face TRL.
We’re sharing a hands-on example showing how to train Tiny Aya to turn it into a tool-calling agent using TRL, unlocking what could become the first *massively multilingual open agent*.
Small model. Global reach. Agent capabilities.
👉 https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
- 1 reply
reacted to
alvdansen's
post with 🔥
1 day ago
Post
1380
Just open-sourced LoRA Gym with Timothy - production-ready training pipeline for character, motion, aesthetic, and style LoRAs on Wan 2.1/2.2, built on musubi-tuner.
16 training templates across Modal (serverless) and RunPod (bare metal) covering T2V, I2V, Lightning-merged, and vanilla variants.
Our current experimentation focus is Wan 2.2, which is why we built on musubi-tuner (kohya-ss). Wan 2.2's DiT uses a Mixture-of-Experts architecture with two separate experts gated by a hard timestep switch - you're training two LoRAs per concept, one for high-noise (composition/motion) and one for low-noise (texture/identity), and loading both at inference. Musubi handles this dual-expert training natively, and our templates build on top of it to manage the correct timestep boundaries, precision settings, and flow shift values so you don't have to debug those yourself. We've also documented bug fixes for undocumented issues in musubi-tuner and validated hyperparameter defaults derived from cross-referencing multiple practitioners' results rather than untested community defaults.
Also releasing our auto-captioning toolkit for the first time. Per-LoRA-type captioning strategies for characters, styles, motion, and objects. Gemini (free) or Replicate backends.
Current hyperparameters reflect consolidated community findings. We've started our own refinement and plan to release specific recommendations and methodology as soon as next week.
Repo: github.com/alvdansen/lora-gym
- 2 replies
reacted to
AbstractPhil's
post with 👀
2 days ago
Post
1250
The Rosetta Stone geometric vocabulary and the ramping up capacity.
What makes this particular invariant special, is the existence within all structures I've tested so far. I had Claude write up the direct article based on what we built together, but I've tested it on many substructures. This is flawed, and I have a series of answers to making it more accurate.
First a reconstruction from the ground up. This means each shape is specifically built upward from the substructure to the point of inductive deviance. This will be less quick at first and then build speed as I optimize like the last system did.
The "saddle" problem; the system detected saddles because there wasn't enough deviance in the shapes to attenuate to more cardinality and more aligned substructures. The blobs were around 30-40% of the overall patches, which interpolated into the others produced a fair approximation.
It MOST DEFINITELY did see those shapes in their voxel complexity. This is real.
https://claude.ai/public/artifacts/bf1256c7-726d-4943-88ad-d6addb263b8b
You can play with a public claude artifact dedicated to viewing the current shape spectrum - and with that know exactly why it's flawed.
The flawed and repetitive shapes. I rapid prototyped and there are multiple redundant shapes that simply don't classify well or at all. Not to mention the rotation simply doesn't help much of the time, or doesn't exist with many shapes. This will be rectified in the next variation.
Projecting to shared latent space as a catalyst to allow growing subjective geoflow matched step variance, rather than simply direct classification. This will theoretically allow for full channel-to-channel invariant features to be mapped from structure to structure, and the very formula that encapsulated them to be directly baked into the math rather than classified as a substructure analysis.
There are many challenges between here and there, so stay tuned my friends as I plot the geometric language of pretrained AI.
What makes this particular invariant special, is the existence within all structures I've tested so far. I had Claude write up the direct article based on what we built together, but I've tested it on many substructures. This is flawed, and I have a series of answers to making it more accurate.
First a reconstruction from the ground up. This means each shape is specifically built upward from the substructure to the point of inductive deviance. This will be less quick at first and then build speed as I optimize like the last system did.
The "saddle" problem; the system detected saddles because there wasn't enough deviance in the shapes to attenuate to more cardinality and more aligned substructures. The blobs were around 30-40% of the overall patches, which interpolated into the others produced a fair approximation.
It MOST DEFINITELY did see those shapes in their voxel complexity. This is real.
https://claude.ai/public/artifacts/bf1256c7-726d-4943-88ad-d6addb263b8b
You can play with a public claude artifact dedicated to viewing the current shape spectrum - and with that know exactly why it's flawed.
The flawed and repetitive shapes. I rapid prototyped and there are multiple redundant shapes that simply don't classify well or at all. Not to mention the rotation simply doesn't help much of the time, or doesn't exist with many shapes. This will be rectified in the next variation.
Projecting to shared latent space as a catalyst to allow growing subjective geoflow matched step variance, rather than simply direct classification. This will theoretically allow for full channel-to-channel invariant features to be mapped from structure to structure, and the very formula that encapsulated them to be directly baked into the math rather than classified as a substructure analysis.
There are many challenges between here and there, so stay tuned my friends as I plot the geometric language of pretrained AI.
- 2 replies
reacted to
ajibawa-2023's
post with 🔥
3 days ago
Post
3092
JavaScript-Code-Large
ajibawa-2023/JavaScript-Code-Large
JavaScript-Code-Large is a large-scale corpus of JavaScript source code comprising around 5 million JavaScript files. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, software engineering automation, and program analysis for the JavaScript ecosystem.
By providing a high-volume, language-specific corpus, JavaScript-Code-Large enables systematic experimentation in JavaScript-focused model training, domain adaptation, and downstream code understanding tasks.
JavaScript-Code-Large addresses the need for a dedicated JavaScript-only dataset at substantial scale, enabling focused research across frontend, backend, and full-stack JavaScript environments. .
ajibawa-2023/JavaScript-Code-Large
JavaScript-Code-Large is a large-scale corpus of JavaScript source code comprising around 5 million JavaScript files. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, software engineering automation, and program analysis for the JavaScript ecosystem.
By providing a high-volume, language-specific corpus, JavaScript-Code-Large enables systematic experimentation in JavaScript-focused model training, domain adaptation, and downstream code understanding tasks.
JavaScript-Code-Large addresses the need for a dedicated JavaScript-only dataset at substantial scale, enabling focused research across frontend, backend, and full-stack JavaScript environments. .
reacted to
ZennyKenny's
post with 🔥
3 days ago
Post
754
👉 Like everyone else, I've been blown away by the possibilities unlocked by OpenClaw (I've got an agent running locally and in a Railway pod that's always alive so I can automate as I ride the metro).
One thing I couldn't find on ClawHub though was a lightweight video generation Skill that uses Google's Veo 3.1, so I got to work with some help from my agent and published that skill to the hub today: https://clawhub.ai/kghamilton89/veo-video-generator
😎 Now your agent can generate SOTA audio/video as you fervently message it from Telegram Messenger demanding minor adjustments. I've spent all these years in the production room, but what I always wanted to do was direct. Feels good man.
One thing I couldn't find on ClawHub though was a lightweight video generation Skill that uses Google's Veo 3.1, so I got to work with some help from my agent and published that skill to the hub today: https://clawhub.ai/kghamilton89/veo-video-generator
😎 Now your agent can generate SOTA audio/video as you fervently message it from Telegram Messenger demanding minor adjustments. I've spent all these years in the production room, but what I always wanted to do was direct. Feels good man.
reacted to
branikita's
post with 🚀
3 days ago
Post
2869
We stress-test the FEETECH STS3215: real backlash (0.87° measured vs spec), repeatability, speed accuracy, stall torque above rating, and thermal overload behavior under continuous load. Practical implications for robot arms and grippers.
Full video: https://www.youtube.com/watch?v=UN5_fZVSWcw
Full video: https://www.youtube.com/watch?v=UN5_fZVSWcw
reacted to
ajibawa-2023's
post with 🚀
4 days ago
Post
3081
Java-Code-Large (
ajibawa-2023/Java-Code-Large)
Java-Code-Large is a large-scale corpus of publicly available Java source code comprising more than 15 million java codes. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, software engineering automation, and program analysis.
By providing a high-volume, language-specific corpus, Java-Code-Large enables systematic experimentation in Java-focused model training, domain adaptation, and downstream code understanding tasks.
Java-Code-Large is a large-scale corpus of publicly available Java source code comprising more than 15 million java codes. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, software engineering automation, and program analysis.
By providing a high-volume, language-specific corpus, Java-Code-Large enables systematic experimentation in Java-focused model training, domain adaptation, and downstream code understanding tasks.
reacted to
evalstate's
post with 🤗
4 days ago
Post
3341
Hugging Face MCP Server v0.3.2
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Replace model_search and dataset_search with combined hub_repo_search tool.
- Less distracting description for hf_doc_search
- model_search and dataset_search tool calls will still function (plan to remove next release).
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Replace model_search and dataset_search with combined hub_repo_search tool.
- Less distracting description for hf_doc_search
- model_search and dataset_search tool calls will still function (plan to remove next release).
- 4 replies
reacted to
Tonic's
post with 🔥
4 days ago
Post
3016
🙋🏻♂️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
reacted to
their
post with 🚀
4 days ago
Post
2462
NEW MODEL:
vanta-research/PE-Type-4-Solene-4B
PE-Type-4-Solene-4B is the fourth release in Project Enneagram from VANTA Research, an initiative to study nuance in AI persona design wherein each of the 9 Enneagram types will be finetuned on the Gemma3 4B architecture.
Solene is finetuned to exhibit the Individualist profile as defined by the Enneagram Institute; emotional honesty/depth, growth & transformation intelligence, and creative expression.
As with the other releases in this project, Solene is perfect for research applications, persona exploration, or self-improvement.
Type 5 soon!
PE-Type-4-Solene-4B is the fourth release in Project Enneagram from VANTA Research, an initiative to study nuance in AI persona design wherein each of the 9 Enneagram types will be finetuned on the Gemma3 4B architecture.
Solene is finetuned to exhibit the Individualist profile as defined by the Enneagram Institute; emotional honesty/depth, growth & transformation intelligence, and creative expression.
As with the other releases in this project, Solene is perfect for research applications, persona exploration, or self-improvement.
Type 5 soon!
posted
an
update
4 days ago
Post
2462
NEW MODEL:
vanta-research/PE-Type-4-Solene-4B
PE-Type-4-Solene-4B is the fourth release in Project Enneagram from VANTA Research, an initiative to study nuance in AI persona design wherein each of the 9 Enneagram types will be finetuned on the Gemma3 4B architecture.
Solene is finetuned to exhibit the Individualist profile as defined by the Enneagram Institute; emotional honesty/depth, growth & transformation intelligence, and creative expression.
As with the other releases in this project, Solene is perfect for research applications, persona exploration, or self-improvement.
Type 5 soon!
PE-Type-4-Solene-4B is the fourth release in Project Enneagram from VANTA Research, an initiative to study nuance in AI persona design wherein each of the 9 Enneagram types will be finetuned on the Gemma3 4B architecture.
Solene is finetuned to exhibit the Individualist profile as defined by the Enneagram Institute; emotional honesty/depth, growth & transformation intelligence, and creative expression.
As with the other releases in this project, Solene is perfect for research applications, persona exploration, or self-improvement.
Type 5 soon!
reacted to
danielhanchen's
post with 🔥
4 days ago
Post
5494
You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.
GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/qwen3.5
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.
GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/qwen3.5
- 9 replies
replied to
boroll2347's
post
4 days ago
Test successful! 🚀
reacted to
danielhanchen's
post with 🔥
6 days ago
Post
8339
You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.
Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.
Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF
- 1 reply
replied to
Ujjwal-Tyagi's
post
8 days ago
I've been using it quite a bit lately. Really been enjoying it so far!