Do we need to add Qwen TTS?
Mahimai Raja J PRO
mahimairaja
AI & ML interests
Azure AI Engineer | LangChain + LangGraph | FastAPI | RAG | Voice AI
Recent Activity
replied to
their
post
about 4 hours ago
My Favorite Open Source Models for Jan 2026
1. General Use - https://huggingface.co/deepseek-ai/DeepSeek-V3.2
2. Reasoning - https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale
3. Coding - https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct
4. OCR - https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct
5. Image Generation - https://huggingface.co/black-forest-labs/FLUX.2-dev
6. Image Editing - https://huggingface.co/Qwen/Qwen-Image-Edit-2509
What model do you use regularly?
posted
an
update
about 4 hours ago
My Favorite Open Source Models for Jan 2026
1. General Use - https://huggingface.co/deepseek-ai/DeepSeek-V3.2
2. Reasoning - https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale
3. Coding - https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct
4. OCR - https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct
5. Image Generation - https://huggingface.co/black-forest-labs/FLUX.2-dev
6. Image Editing - https://huggingface.co/Qwen/Qwen-Image-Edit-2509
What model do you use regularly?
published
a Space
1 day ago
mahimairaja/my-llm-finetunings
Organizations
replied to
their
post
about 4 hours ago
posted
an
update
about 4 hours ago
Post
39
My Favorite Open Source Models for Jan 2026
1. General Use - deepseek-ai/DeepSeek-V3.2
2. Reasoning - deepseek-ai/DeepSeek-V3.2-Speciale
3. Coding - Qwen/Qwen3-Coder-30B-A3B-Instruct
4. OCR - Qwen/Qwen3-VL-8B-Instruct
5. Image Generation - black-forest-labs/FLUX.2-dev
6. Image Editing - Qwen/Qwen-Image-Edit-2509
What model do you use regularly?
1. General Use - deepseek-ai/DeepSeek-V3.2
2. Reasoning - deepseek-ai/DeepSeek-V3.2-Speciale
3. Coding - Qwen/Qwen3-Coder-30B-A3B-Instruct
4. OCR - Qwen/Qwen3-VL-8B-Instruct
5. Image Generation - black-forest-labs/FLUX.2-dev
6. Image Editing - Qwen/Qwen-Image-Edit-2509
What model do you use regularly?
-
- 2 replies
posted
an
update
1 day ago
Post
482
Lacking vllm support for Transformers v5, frustrating only me?
replied to
davidmezzetti's
post
5 days ago
Good work!
reacted to
davidmezzetti's
post with 👍
5 days ago
Post
1173
Tired of paying a bunch of money for large LLMs? Then read this notebook and/or watch this video on how to distill knowledge into tiny LLMs.
Notebook: https://github.com/neuml/txtai/blob/master/examples/80_Distilling_Knowledge_into_Tiny_LLMs.ipynb
Video: https://www.youtube.com/watch?v=Ol560ktgkf0
Notebook: https://github.com/neuml/txtai/blob/master/examples/80_Distilling_Knowledge_into_Tiny_LLMs.ipynb
Video: https://www.youtube.com/watch?v=Ol560ktgkf0
-
- 6 replies
reacted to
unmodeled-tyler's
post with 👍
5 days ago
Post
3672
NEW MODEL:
vanta-research/mox-tiny-1
Excited to share the first model from the new Mox-1 model family from VANTA Research!
Mox-Tiny-1 is finetuned from Llama's 3.1 8B architecture specifically for thinking partnership and high-fidelity AI interaction.
Training domains were carefully selected with this goal in mind, and all datasets used were synthetically generated for the Mox-1 models specifically.
Domains include but not limited to:
- Direct opinions (clear stances on various topics)
- Constructive disagreement (Pushing back on flawed premises)
- Epistemic confidence (calibrated certainty and uncertainty)
- Warmth & presence (Empathetic, human responses)
- Wonder & puzzlement (Intellectual curiosity)
Interaction Examples:
Direct opinions:
Warmth & Humor:
Mox-Tiny-1 is our first release in this new model family, with Mox-Small-1 (~32B) to follow soon!
Excited to share the first model from the new Mox-1 model family from VANTA Research!
Mox-Tiny-1 is finetuned from Llama's 3.1 8B architecture specifically for thinking partnership and high-fidelity AI interaction.
Training domains were carefully selected with this goal in mind, and all datasets used were synthetically generated for the Mox-1 models specifically.
Domains include but not limited to:
- Direct opinions (clear stances on various topics)
- Constructive disagreement (Pushing back on flawed premises)
- Epistemic confidence (calibrated certainty and uncertainty)
- Warmth & presence (Empathetic, human responses)
- Wonder & puzzlement (Intellectual curiosity)
Interaction Examples:
Direct opinions:
User: What's the best programming language?
Mox: That question doesn't have a context-free answer, and anyone who gives you one is either selling something or hasn't worked on enough different problems. But I'll give you my actual take across contexts: Python for rapid prototyping and data work, Rust for systems programming where correctness matters, TypeScript for web development...Warmth & Humor:
User: I've been debugging this issue for six hours.
Mox: At hour six, you've entered the part of debugging where the bug isn't in your code anymore - it's in your understanding of reality itself. The semicolon starts looking suspicious. Show me what you're dealing with. Fresh eyes help, and mine haven't been staring at it since lunch.Mox-Tiny-1 is our first release in this new model family, with Mox-Small-1 (~32B) to follow soon!
-
- 5 replies
Apparently, quantized versions are yet to arrive
Does vllm support WeDLM architecture?
reacted to
AdinaY's
post with 👍
13 days ago
Post
1516
Wechat AI is shipping!
WeDLM 🔥 A new language model that generates tokens in parallel, making it faster than standard LLMs , with the same Transformer setup!
https://huggingface.co/collections/tencent/wedlm
✨ 7B/8B - Base & Instruct
✨ Apache 2.0
WeDLM 🔥 A new language model that generates tokens in parallel, making it faster than standard LLMs , with the same Transformer setup!
https://huggingface.co/collections/tencent/wedlm
✨ 7B/8B - Base & Instruct
✨ Apache 2.0
-
-
- 4 replies
reacted to
unmodeled-tyler's
post with 🚀
13 days ago
Post
1403
Atom-80B is out!:
vanta-research/atom-80b
I'm excited to share the new Atom-80B from VANTA Research! A few days ago we released the largest model-to-date from our portfolio, which was Atom-27B.
We've quickly scaled up to the new Qwen3 Next 80B architecture, bringing our friendly, curious, and collaborative Atom persona to cutting edge lightweight, high parameter inference.
Atom is designed to work and think alongside you through curious exploration. Using Atom collaboratively in your work can help spark your own creativity or curiosity. Give it a try!
I'm excited to share the new Atom-80B from VANTA Research! A few days ago we released the largest model-to-date from our portfolio, which was Atom-27B.
We've quickly scaled up to the new Qwen3 Next 80B architecture, bringing our friendly, curious, and collaborative Atom persona to cutting edge lightweight, high parameter inference.
Atom is designed to work and think alongside you through curious exploration. Using Atom collaboratively in your work can help spark your own creativity or curiosity. Give it a try!
- 1 reply
reacted to
hypothetical's
post with 🔥
13 days ago
Post
2014
We have updated our transcription model:
TheStageAI/thewhisper-large-v3-turbo
– 6.00 WER on the English Open ASR Leaderboard
– 4.74 WER on the Multilingual Open ASR Leaderboard
– Beats NVIDIA Parakeet (6.34 WER) and Whisper-large-v3-turbo (7.8 WER)
– Strong improvements in Arabic, Hindi, Chinese
– Maintains quality with background and environmental noise
– Optimized inference engines for NVIDIA and Apple
– Hugging Face Transformers interface for easy use
– Best-in-class speed on NVIDIA GPUs and power efficiency on Apple devices
– NVIDIA Jetson Thor support
– 6.00 WER on the English Open ASR Leaderboard
– 4.74 WER on the Multilingual Open ASR Leaderboard
– Beats NVIDIA Parakeet (6.34 WER) and Whisper-large-v3-turbo (7.8 WER)
– Strong improvements in Arabic, Hindi, Chinese
– Maintains quality with background and environmental noise
– Optimized inference engines for NVIDIA and Apple
– Hugging Face Transformers interface for easy use
– Best-in-class speed on NVIDIA GPUs and power efficiency on Apple devices
– NVIDIA Jetson Thor support
-
- 2 replies
reacted to
kanaria007's
post with 👍
13 days ago
Post
1991
✅ New Article: *PoC Architecture for Education & Developmental Support*
Title:
🎓 Building an SI-Core Wrapped Learning Companion - PoC architecture for education and developmental support
🔗 https://huggingface.co/blog/kanaria007/poc-architecture-for-education-development-support
---
Summary:
Most “AI tutors” are built as *LLM-first* systems. This article flips the default:
* The LLM is treated as an *untrusted proposal engine*
* *SI-Core owns* observation, consent, ethics, memory, and rollback
* Teachers and guardians get *real oversight*, not just chat transcripts
Scoped intentionally to *one subject × a small cohort (10–30 learners)*, this is a PoC you can actually ship—and audit.
> Don’t ask: “Can an AI replace teachers?”
> Prove: “Can we make an AI companion *safe, explainable, and governable* for real learners?”
---
Why It Matters (for AI on real stacks):
• *Consent & accommodations* are first-class (especially for minors / neurodivergent learners)
• *Ethics decisions are logged* (ALLOW / DENY / ESCALATE) with traceable reasoning
• “*Why this?*” explanations are built in for learners—and deeper inspection for adults
---
What’s Inside:
• A minimal reference architecture (frontend → SI-Gate → ethics/memory/logging → LLM APIs)
• Non-negotiables for the pilot (SI-wrapped LLM, Effect Ledger, ethics overlay, dashboards)
• Failure modes + safe-mode behavior
• Implementation checklist + rough effort/cost ballparks (kept explicitly non-normative)
---
📖 Structured Intelligence Engineering Series
A deployable pattern for taking today’s LLM tutor ideas and making them *auditable, overrideable, and rollback-safe*.
Title:
🎓 Building an SI-Core Wrapped Learning Companion - PoC architecture for education and developmental support
🔗 https://huggingface.co/blog/kanaria007/poc-architecture-for-education-development-support
---
Summary:
Most “AI tutors” are built as *LLM-first* systems. This article flips the default:
* The LLM is treated as an *untrusted proposal engine*
* *SI-Core owns* observation, consent, ethics, memory, and rollback
* Teachers and guardians get *real oversight*, not just chat transcripts
Scoped intentionally to *one subject × a small cohort (10–30 learners)*, this is a PoC you can actually ship—and audit.
> Don’t ask: “Can an AI replace teachers?”
> Prove: “Can we make an AI companion *safe, explainable, and governable* for real learners?”
---
Why It Matters (for AI on real stacks):
• *Consent & accommodations* are first-class (especially for minors / neurodivergent learners)
• *Ethics decisions are logged* (ALLOW / DENY / ESCALATE) with traceable reasoning
• “*Why this?*” explanations are built in for learners—and deeper inspection for adults
---
What’s Inside:
• A minimal reference architecture (frontend → SI-Gate → ethics/memory/logging → LLM APIs)
• Non-negotiables for the pilot (SI-wrapped LLM, Effect Ledger, ethics overlay, dashboards)
• Failure modes + safe-mode behavior
• Implementation checklist + rough effort/cost ballparks (kept explicitly non-normative)
---
📖 Structured Intelligence Engineering Series
A deployable pattern for taking today’s LLM tutor ideas and making them *auditable, overrideable, and rollback-safe*.
reacted to
Ujjwal-Tyagi's
post with 👍
13 days ago
Post
2678
For more better details and analysis, you can read the article here: https://huggingface.co/blog/Ujjwal-Tyagi/steering-not-censoring, We are sleepwalking into a crisis. I am deeply concerned about AI model safety right now because, as the community rushes to roll out increasingly powerful open-source models, we are completely neglecting the most critical aspect: safety. It seems that nobody is seriously thinking about the potential consequences of unregulated model outputs or the necessity of robust guardrails. We are essentially planting the seeds for our own destruction if we prioritize raw performance over security.
This negligence is terrifyingly evident when you look at the current landscape. Take Qwen Image 2512, for example; while it delivers undeniably strong performance, it has incredibly weak guardrails that make it dangerous to deploy. In stark contrast, Z Image might not get as much hype for its power, but it has much better safety guardrails than Qwen Image 2512.
It is imperative that the open-source community and developers recognize that capability without responsibility is a liability. We must actively work on protecting these models from bad actors who seek to exploit them for malicious purposes, such as generating disinformation, creating non-consensual imagery, or automating cyberattacks. It is no longer enough to simply release a powerful model; we must build layers of defense that make it resistant to jailbreaking and adversarial attacks. Developers need to prioritize alignment and robust filtering techniques just as much as they prioritize benchmark scores. We cannot hand such potent tools to the world without ensuring they have the safety mechanisms to prevent them from being turned against us.
This negligence is terrifyingly evident when you look at the current landscape. Take Qwen Image 2512, for example; while it delivers undeniably strong performance, it has incredibly weak guardrails that make it dangerous to deploy. In stark contrast, Z Image might not get as much hype for its power, but it has much better safety guardrails than Qwen Image 2512.
It is imperative that the open-source community and developers recognize that capability without responsibility is a liability. We must actively work on protecting these models from bad actors who seek to exploit them for malicious purposes, such as generating disinformation, creating non-consensual imagery, or automating cyberattacks. It is no longer enough to simply release a powerful model; we must build layers of defense that make it resistant to jailbreaking and adversarial attacks. Developers need to prioritize alignment and robust filtering techniques just as much as they prioritize benchmark scores. We cannot hand such potent tools to the world without ensuring they have the safety mechanisms to prevent them from being turned against us.
-
- 17 replies
replied to
SkorczyByk's
post
13 days ago
I would suggest checking out - olmocr
reacted to
SkorczyByk's
post with 👍
13 days ago
Post
2308
Potrzebuję modelu do analizy długich dokumentów technicznych, z wzorami, tabelami, wykresami, formułami matematycznymi.
-
-
- 2 replies
reacted to
their
post with 🚀
21 days ago
Post
4778
Happy New Years 2026!
For next 365 days I will be commit to work on:
- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents
For next 365 days I will be commit to work on:
- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents
- 1 reply
posted
an
update
21 days ago
Post
4778
Happy New Years 2026!
For next 365 days I will be commit to work on:
- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents
For next 365 days I will be commit to work on:
- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents
-
- 1 reply
replied to
burtenshaw's
post
11 months ago
This look great! but can we attach VAD or interrupt when human speaks?