Qwen/Qwen-AgentWorld-35B-A3B
Text Generation • 35B • Updated • 223 • 151
Alex Hant
hardhant
AI & ML interests
None yet
Recent Activity
liked a model about 7 hours ago
Qwen/Qwen-AgentWorld-35B-A3B liked a model 2 days ago
ASLP-lab/DiffRhythm-1_2-full liked a model 2 days ago
HeartMuLa/HeartMuLaGenOrganizations
None yet
liked a
model about 7 hours ago
liked 2
models 2 days ago
reacted to projectlosangeles's post with ❤️ 2 days ago
Post
9398
🔥Check out HeartMuLa!!! 🔥
The best open-sourced music generation model in terms of lyrics controllability and music quality!!!
🤗https://huggingface.co/HeartMuLa/HeartMuLa-oss-3B-happy-new-year🤗
❤️Listen to amazing HeartMuLa output samples here:
https://soundcloud.com/aleksandr-sigalov-61/sets/heartmula ❤️
@victor
The best open-sourced music generation model in terms of lyrics controllability and music quality!!!
🤗https://huggingface.co/HeartMuLa/HeartMuLa-oss-3B-happy-new-year🤗
❤️Listen to amazing HeartMuLa output samples here:
https://soundcloud.com/aleksandr-sigalov-61/sets/heartmula ❤️
@victor
- 4 replies
liked a
Space 4 days ago
liked a
model 4 days ago
reacted to ajibawa-2023's post with 🚀 4 days ago
Post
6772
Shell-Code-Large
Dataset: ajibawa-2023/Shell-Code-Large
Shell-Code-Large is a large-scale corpus of Shell scripting source code comprising approximately 640,000 code samples stored in JSON Lines (.jsonl) format. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, DevOps automation, cloud infrastructure engineering, system administration, and software engineering automation.
By providing a high-volume, language-specific corpus focused exclusively on Shell scripting, Shell-Code-Large enables systematic experimentation in automation workflows, deployment pipelines, infrastructure management, and command-line tooling. These domains remain foundational to Linux systems, cloud-native platforms, CI/CD environments, and modern DevOps practices.
Shell-Code-Large addresses the need for a dedicated Shell-focused dataset at substantial scale, enabling targeted research into scripting patterns, command composition, workflow orchestration, infrastructure automation, and operational engineering practices
Dataset: ajibawa-2023/Shell-Code-Large
Shell-Code-Large is a large-scale corpus of Shell scripting source code comprising approximately 640,000 code samples stored in JSON Lines (.jsonl) format. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, DevOps automation, cloud infrastructure engineering, system administration, and software engineering automation.
By providing a high-volume, language-specific corpus focused exclusively on Shell scripting, Shell-Code-Large enables systematic experimentation in automation workflows, deployment pipelines, infrastructure management, and command-line tooling. These domains remain foundational to Linux systems, cloud-native platforms, CI/CD environments, and modern DevOps practices.
Shell-Code-Large addresses the need for a dedicated Shell-focused dataset at substantial scale, enabling targeted research into scripting patterns, command composition, workflow orchestration, infrastructure automation, and operational engineering practices
liked a
model 6 days ago
reacted to owensong's post with 🔥 6 days ago
Post
6405
I just released Inflect-Nano-v1, an ultra-small 4.63 parameter text-to-speech model.
The main idea is simple: instead of only making the acoustic model tiny and relying on a larger external vocoder, Inflect-Nano-v1 keeps the complete text-to-waveform stack under 5M parameters.
Quick facts:
- 4.63M total inference parameters
- 3.46M acoustic model
- 1.17M vocoder
- 24 kHz audio
- English-only
- Single male voice
- Runs locally with a simple PyTorch inference script
Why I made it:
Most modern TTS models are much larger, and even many “small TTS” projects depend on a separate vocoder. I wanted to see how far a complete tiny TTS stack could be pushed while still producing usable speech.
It is not SOTA, and I am not trying to claim it competes with large TTS systems. The interesting part is the size-to-functionality ratio.
What works:
It can generate arbitrary English speech locally, and the model is small enough to be interesting for:
- local voice assistants
- embedded/edge experiments
- browser or WASM-style TTS exploration
- efficient inference research
- tiny-model baselines
Limitations:
The quality is still limited. It can sound robotic, stumble on difficult unseen text, and the vocoder is still a clear bottleneck. Long or unusual prompts are less reliable.
So I would frame this as a research/demo release, not a production TTS engine.
I’d love feedback from people interested in:
- tiny speech models
- vocoders
- local TTS
- efficient inference
- embedded speech synthesis
- improving small-model generalization
If people find it useful, I’m interested in putting more training budget into a stronger v2.
Model page:
owensong/Inflect-Nano-v1
The main idea is simple: instead of only making the acoustic model tiny and relying on a larger external vocoder, Inflect-Nano-v1 keeps the complete text-to-waveform stack under 5M parameters.
Quick facts:
- 4.63M total inference parameters
- 3.46M acoustic model
- 1.17M vocoder
- 24 kHz audio
- English-only
- Single male voice
- Runs locally with a simple PyTorch inference script
Why I made it:
Most modern TTS models are much larger, and even many “small TTS” projects depend on a separate vocoder. I wanted to see how far a complete tiny TTS stack could be pushed while still producing usable speech.
It is not SOTA, and I am not trying to claim it competes with large TTS systems. The interesting part is the size-to-functionality ratio.
What works:
It can generate arbitrary English speech locally, and the model is small enough to be interesting for:
- local voice assistants
- embedded/edge experiments
- browser or WASM-style TTS exploration
- efficient inference research
- tiny-model baselines
Limitations:
The quality is still limited. It can sound robotic, stumble on difficult unseen text, and the vocoder is still a clear bottleneck. Long or unusual prompts are less reliable.
So I would frame this as a research/demo release, not a production TTS engine.
I’d love feedback from people interested in:
- tiny speech models
- vocoders
- local TTS
- efficient inference
- embedded speech synthesis
- improving small-model generalization
If people find it useful, I’m interested in putting more training budget into a stronger v2.
Model page:
owensong/Inflect-Nano-v1
liked 2
models 7 days ago
reacted to prithivMLmods's post with 🔥 8 days ago
Post
3847
Wan2.2-I2V-Fast with highly upscaled sequential frame sampling is now available as a Spaces demo, built using Wan2.2-I2V and FLUX.2-Klein. Try the demo using the links below.👇
➠ wan2.2-i2v-fast : prithivMLmods/wan2.2-i2v-fast
➠ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
➠ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
⤷ To learn more, visit the app page or the respective model pages.
➠ wan2.2-i2v-fast : prithivMLmods/wan2.2-i2v-fast
➠ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
➠ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
⤷ To learn more, visit the app page or the respective model pages.
liked a
model 9 days ago
liked 2
models 10 days ago
reacted to kasbsquall's post with 🔥 12 days ago
Post
4181
🔎 UX Crime Scene — every interface hides a crime.
Drop a screenshot of ANY website or app, and THE INSPECTOR — a film-noir detective — works it as a crime scene: he circles each UX flaw on the real pixels, names the charge, and files a verdict with a letter grade. A UX audit that plays like a detective thriller.
But the verdict is just the opening statement. Now it goes further:
⚖️ THE TRIAL — put the interface on trial. The guilty UI elements take the stand and defend themselves while the Inspector rules from the evidence.
🖼️ THE RECONSTRUCTION — one click and FLUX.2 Klein rebuilds the worst element FIXED, live. Before/after, on the real pixels.
🔊 THE VOICE — hear the verdict read aloud (Kokoro, local, no keys).
🚨 MOST WANTED — a public rogues' gallery. Book your case onto a shared board where the city's worst interfaces are ranked by their crimes. Booked by the public.
Three small models, all on Modal (scale-to-zero), none over 32B:
👁️ Qwen2.5-VL-7B (vision agent) · 🖼️ FLUX.2 Klein (reconstruction) · 🔊 Kokoro-82M (voice)
📊 Human-graded: 84% grounding / 92% valid charges.
▶️ Trailer: https://youtu.be/6u58YIEPrkA
📹 Full walkthrough: https://youtu.be/WyQbY0XJ_9E
🕵️ Try it: build-small-hackathon/ux-crime-scene
Built solo for #BuildSmallHackathon (Gradio × Hugging Face). Open the case — the Inspector is waiting.
Drop a screenshot of ANY website or app, and THE INSPECTOR — a film-noir detective — works it as a crime scene: he circles each UX flaw on the real pixels, names the charge, and files a verdict with a letter grade. A UX audit that plays like a detective thriller.
But the verdict is just the opening statement. Now it goes further:
⚖️ THE TRIAL — put the interface on trial. The guilty UI elements take the stand and defend themselves while the Inspector rules from the evidence.
🖼️ THE RECONSTRUCTION — one click and FLUX.2 Klein rebuilds the worst element FIXED, live. Before/after, on the real pixels.
🔊 THE VOICE — hear the verdict read aloud (Kokoro, local, no keys).
🚨 MOST WANTED — a public rogues' gallery. Book your case onto a shared board where the city's worst interfaces are ranked by their crimes. Booked by the public.
Three small models, all on Modal (scale-to-zero), none over 32B:
👁️ Qwen2.5-VL-7B (vision agent) · 🖼️ FLUX.2 Klein (reconstruction) · 🔊 Kokoro-82M (voice)
📊 Human-graded: 84% grounding / 92% valid charges.
▶️ Trailer: https://youtu.be/6u58YIEPrkA
📹 Full walkthrough: https://youtu.be/WyQbY0XJ_9E
🕵️ Try it: build-small-hackathon/ux-crime-scene
Built solo for #BuildSmallHackathon (Gradio × Hugging Face). Open the case — the Inspector is waiting.
- 1 reply
liked 2
models 12 days ago
liked a
model 13 days ago
reacted to danielhanchen's post with 🔥 14 days ago
Post
1050
Google releases DiffusionGemma.✨
The new 26B-A4B diffusion text model runs locally on 18GB RAM.
Run with 4x faster text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio.
GGUF: unsloth/diffusiongemma-26B-A4B-it-GGUF
Guide: https://unsloth.ai/docs/models/diffusiongemma
The new 26B-A4B diffusion text model runs locally on 18GB RAM.
Run with 4x faster text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio.
GGUF: unsloth/diffusiongemma-26B-A4B-it-GGUF
Guide: https://unsloth.ai/docs/models/diffusiongemma
- 1 reply