Reubencf/konkani-gemma-train
Viewer
•
Updated
•
92.2k
Reuben fernandes PRO
Reubencf
AI & ML interests
LLM
Recent Activity
published
a dataset
31 minutes ago
Reubencf/konkani-gemma-train
published
a dataset
31 minutes ago
Reubencf/konkani-gemma-validate
published
a model
about 3 hours ago
Reubencf/konkani-llama3.1-8b-instruct
Organizations
published
2
datasets
31 minutes ago
published
a
model
about 3 hours ago
reacted to
seyf1elislam's
post with 🔥
about 13 hours ago
Post
606
# 🚀 Run Qwen3-TTS on Colab GPU or Locally
Run **Qwen3-TTS (Text-to-Speech & Voice Cloning)** with minimal effort. This setup is based on the official HF Space.
### đź”— Links
* **Official Space:** Qwen/Qwen3-TTS
* **GitHub Repo:** https://github.com/seyf1elislam/qwen-tts-webui-notebook
* **Colab:** https://github.com/seyf1elislam/qwen-tts-webui-notebook/blob/main/Qwen_TTS_(TTS_%26_Voice_Cloning)_Colab.ipynb
---
### đź““ Method 1: Google Colab (Fastest)
1. Open the https://github.com/seyf1elislam/qwen-tts-webui-notebook/blob/main/Qwen_TTS_(TTS_%26_Voice_Cloning)_Colab.ipynb.
2. Add your HF_TOKEN to Google Colab Secrets
3. Ensure you are on a **T4 GPU** runtime.
4. Run all cells. Use the
---
### đź’» Method 2: Local Installation
Requires an GPU. Uses
Run **Qwen3-TTS (Text-to-Speech & Voice Cloning)** with minimal effort. This setup is based on the official HF Space.
### đź”— Links
* **Official Space:** Qwen/Qwen3-TTS
* **GitHub Repo:** https://github.com/seyf1elislam/qwen-tts-webui-notebook
* **Colab:** https://github.com/seyf1elislam/qwen-tts-webui-notebook/blob/main/Qwen_TTS_(TTS_%26_Voice_Cloning)_Colab.ipynb
---
### đź““ Method 1: Google Colab (Fastest)
1. Open the https://github.com/seyf1elislam/qwen-tts-webui-notebook/blob/main/Qwen_TTS_(TTS_%26_Voice_Cloning)_Colab.ipynb.
2. Add your HF_TOKEN to Google Colab Secrets
3. Ensure you are on a **T4 GPU** runtime.
4. Run all cells. Use the
gradio.live link to open the UI.---
### đź’» Method 2: Local Installation
Requires an GPU. Uses
uv for faster setup.# 1. Install uv & Clone
pip install uv
git clone https://huggingface.co/spaces/Qwen/Qwen3-TTS && cd Qwen3-TTS
# 2. Setup Environment
uv venv
uv pip install -r requirements.txt
# 3. Auth & Run
uvx hf auth login
python app.py
# UI available at: http://localhost:7860/
reacted to
kostakoff's
post with đź‘Ť
about 13 hours ago
Post
585
I created list of models based on permissive license (apache2, mit, openrail) and raw fp16 weights.
LLM:
- Mistral 7b v1
- Falcon 7b
- GLM4 9b
- Olmo3 7b
- Yi 9b
- Qwen3 8b
- Internlm3 8B
- PHI4
Multimodal LLM:
- Pixtral 12b
- Qwen3-VL-8B-Instruct
Picture generation:
- Stable Diffusion 1.5
- Stable Diffusion 2.0
- Stable Diffusion XL
Video generation:
- WAN 2.1 VACE Diffusers
TTS:
- SUNO Bark
This can be very useful for those who are just starting their AI LLM journey in PyTorch, like me.
Suggestions in the comments are welcome.
LLM:
- Mistral 7b v1
- Falcon 7b
- GLM4 9b
- Olmo3 7b
- Yi 9b
- Qwen3 8b
- Internlm3 8B
- PHI4
Multimodal LLM:
- Pixtral 12b
- Qwen3-VL-8B-Instruct
Picture generation:
- Stable Diffusion 1.5
- Stable Diffusion 2.0
- Stable Diffusion XL
Video generation:
- WAN 2.1 VACE Diffusers
TTS:
- SUNO Bark
This can be very useful for those who are just starting their AI LLM journey in PyTorch, like me.
Suggestions in the comments are welcome.
reacted to
tegridydev's
post with 👀❤️
about 13 hours ago
Post
1678
Introducing OpenMALx
openmalx
Repository for Infosec and Machine Learning Resources
OpenMALx is an organization focused on the development of datasets and models for security analysis. The project objective is to provide structured data for training and evaluating large language models in a security context.
---
Technical Focus
**Dataset Formatting:** Processing raw security tool logs into instruction/response pairs for model training.
**Local Execution:** Optimizing models for local hardware to ensure data remains on-premises.
**Response Logic:** Developing structured formats for explaining security vulnerabilities and remediation steps.
Active Projects
**infosec-tool-output:** A dataset mapping static and dynamic analysis tool outputs to technical summaries.
openmalx/infosec-tool-output
**open-malsec:** A collection of text-based security threats, including phishing and social engineering samples, for classification tasks.
openmalx/open-malsec
Repository for Infosec and Machine Learning Resources
OpenMALx is an organization focused on the development of datasets and models for security analysis. The project objective is to provide structured data for training and evaluating large language models in a security context.
---
Technical Focus
**Dataset Formatting:** Processing raw security tool logs into instruction/response pairs for model training.
**Local Execution:** Optimizing models for local hardware to ensure data remains on-premises.
**Response Logic:** Developing structured formats for explaining security vulnerabilities and remediation steps.
Active Projects
**infosec-tool-output:** A dataset mapping static and dynamic analysis tool outputs to technical summaries.
openmalx/infosec-tool-output
**open-malsec:** A collection of text-based security threats, including phishing and social engineering samples, for classification tasks.
openmalx/open-malsec
reacted to
AdinaY's
post with 🔥
about 13 hours ago
Post
646
Kimi K2.5 from Moonshot AI is more than just another large model🤯
https://huggingface.co/collections/moonshotai/kimi-k25
✨ Native multimodality : image + video + language + agents 💥
✨1T MoE / 32B active
✨ 256K context
✨ Modified MIT license
✨ Agent Swarm execution
✨ Open weights + open infra mindset
https://huggingface.co/collections/moonshotai/kimi-k25
✨ Native multimodality : image + video + language + agents 💥
✨1T MoE / 32B active
✨ 256K context
✨ Modified MIT license
✨ Agent Swarm execution
✨ Open weights + open infra mindset
reacted to
kanaria007's
post with đź‘Ť
about 13 hours ago
Post
1478
âś… New Article: *Post-Transformer Decision Cores* (v0.1)
Title:
🚀 Post-Transformer Decision Cores: Goal-Native Engines Beyond LLMs
đź”— https://huggingface.co/blog/kanaria007/post-tranformer-decision-cores
---
Summary:
Transformers are powerful—but in SI-Core they’re *not the essence of intelligence*. A *Decision Core* is anything that satisfies the *Jump contracts* (OBS/ETH/MEM/ID/EVAL + RML), and those contracts don’t require next-token prediction.
This article sketches what “post-Transformer” looks like in practice: *goal-native, structure-aware controllers* that may use LLMs as tools—but don’t depend on them as the runtime brain.
> Don’t relax the contracts.
> Replace the engine behind them.
---
Why It Matters:
• Makes LLMs *optional*: shift them to “genesis / exploration / explanation,” while routine high-stakes Jumps run on structured cores
• Improves boring-but-critical properties: *determinism (CAS), fewer inconsistencies (SCI), fewer ETH violations (EAI), better rollback (RBL/RIR)*
• Enables gradual adoption via *pluggable Jump engines* and domain-by-domain “primary vs fallback” switching
---
What’s Inside:
• The architectural inversion: *World → OBS → SIM/SIS → Jump (Decision Core) → RML → Effects* (LLM is just one engine)
• Three compatible post-Transformer directions:
1. *World-model + search controllers* (MPC/MCTS/anytime search with explicit GCS + ETH constraints)
2. *Genius-distilled specialized controllers* (distill structure from GeniusTraces; LLM becomes a “genesis tool”)
3. *SIL-compiled Decision Programs* (typed Jump entrypoints, compiler-checked invariants, DPIR/GSPU targeting)
• A realistic migration path: LLM-wrapped → Genius library → shadow dual-run → flip primary by domain → SIL-compiled cores
• How this connects to “reproducing genius”: GRP provides trace selection/format; this article provides the engine architectures
---
đź“– Structured Intelligence Engineering Series
Title:
🚀 Post-Transformer Decision Cores: Goal-Native Engines Beyond LLMs
đź”— https://huggingface.co/blog/kanaria007/post-tranformer-decision-cores
---
Summary:
Transformers are powerful—but in SI-Core they’re *not the essence of intelligence*. A *Decision Core* is anything that satisfies the *Jump contracts* (OBS/ETH/MEM/ID/EVAL + RML), and those contracts don’t require next-token prediction.
This article sketches what “post-Transformer” looks like in practice: *goal-native, structure-aware controllers* that may use LLMs as tools—but don’t depend on them as the runtime brain.
> Don’t relax the contracts.
> Replace the engine behind them.
---
Why It Matters:
• Makes LLMs *optional*: shift them to “genesis / exploration / explanation,” while routine high-stakes Jumps run on structured cores
• Improves boring-but-critical properties: *determinism (CAS), fewer inconsistencies (SCI), fewer ETH violations (EAI), better rollback (RBL/RIR)*
• Enables gradual adoption via *pluggable Jump engines* and domain-by-domain “primary vs fallback” switching
---
What’s Inside:
• The architectural inversion: *World → OBS → SIM/SIS → Jump (Decision Core) → RML → Effects* (LLM is just one engine)
• Three compatible post-Transformer directions:
1. *World-model + search controllers* (MPC/MCTS/anytime search with explicit GCS + ETH constraints)
2. *Genius-distilled specialized controllers* (distill structure from GeniusTraces; LLM becomes a “genesis tool”)
3. *SIL-compiled Decision Programs* (typed Jump entrypoints, compiler-checked invariants, DPIR/GSPU targeting)
• A realistic migration path: LLM-wrapped → Genius library → shadow dual-run → flip primary by domain → SIL-compiled cores
• How this connects to “reproducing genius”: GRP provides trace selection/format; this article provides the engine architectures
---
đź“– Structured Intelligence Engineering Series
reacted to
AdinaY's
post with 🔥
about 13 hours ago
Post
731
Big day in open source AI!!
✨ DeepSeek released OCR2 💥
deepseek-ai/DeepSeek-OCR-2
✨ Kimi K2.5 just landed 🔥
moonshotai/Kimi-K2.5
With the Chinese Spring Festival 3 weeks away,
what’s coming next?👀
✨ DeepSeek released OCR2 💥
deepseek-ai/DeepSeek-OCR-2
✨ Kimi K2.5 just landed 🔥
moonshotai/Kimi-K2.5
With the Chinese Spring Festival 3 weeks away,
what’s coming next?👀
reacted to
IlyasMoutawwakil's
post with 🔥
about 13 hours ago
Post
2297
Transformers v5 just landed! 🚀
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.
My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇
Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.
In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.
Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.
Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.
Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...
Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.
My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇
Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.
In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.
Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.
Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.
Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...
Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
- 3 replies
updated
2
datasets
about 16 hours ago
liked
a
model
about 19 hours ago
upvoted
a
collection
about 19 hours ago
liked
5
models
about 21 hours ago
Pacific-Prime/pacific-prime-math-depth00
Robotics
•
Updated
•
2
Pacific-Prime/pacific-prime-math-depth01
Robotics
•
Updated
•
2
Pacific-Prime/pacific-prime-code-depth01
Robotics
•
Updated
•
2
Pacific-Prime/pacific-prime-math-depth02
Robotics
•
Updated
•
2
Pacific-Prime/pacific-prime-code-depth00
Robotics
•
Updated
•
2