Mel Massadian's picture

Mel Massadian

melmass

·

https://melmassadian.com

AI & ML interests

Building tools on top of Generative AI & LLM models

Recent Activity

liked a model about 10 hours ago

hexgrad/Kokoro-82M

liked a model about 20 hours ago

stabilityai/stable-point-aware-3d

reacted to merve's post with 🔥 about 20 hours ago

ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license 💗 https://huggingface.co/collections/ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093 > The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos ⏯️ > The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint) > The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM 💬 the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks ⤵️ > Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.

View all activity

Organizations

melmass's activity

New activity in Kijai/LivePortrait_safetensors 17 days ago

fix 🐛: use safetensors for landmark_model

#5 opened 17 days ago by

New activity in GoodiesHere/Apollo-LMMs-Apollo-7B-t32 19 days ago

Where is the python library?

#1 opened 19 days ago by

New activity in bartowski/Llama-3.1-8B-Lexi-Uncensored-GGUF 5 months ago

wrong number of tensors; expected 292, got 291

#1 opened 6 months ago by

New activity in akjindal53244/Llama-3.1-Storm-8B-GGUF 5 months ago

[BUG] Ollama import fail (wrong number of tensors; expected 292, got 291)

#1 opened 5 months ago by

New activity in meta-llama/Llama-3.1-8B-Instruct 5 months ago

Wrong number of tensors; expected 292, got 291

#69 opened 5 months ago by

New activity in XLabs-AI/flux-controlnet-canny 5 months ago

Training details

#10 opened 5 months ago by

New activity in ByteDance/AnimateDiff-Lightning 7 months ago

Update README.md

#28 opened 7 months ago by

Rename README.md to README.md A man is driving down a country road when he realizes his car is running out of gas. He spots a farm in the distance and decides to stop there for help. The farmer, a friendly man, offers him some gas and starts a conversation. "Did you know," says the farmer, "that we have a cow here on the farm that can tell jokes?" "Really?" the man responds, incredulous. "I'd love to see that." The farmer leads him to the barn, where the cow is standing. He whispers something in the cow's ear, and then the cow looks at the man and says: "Mooo... do you know why the cow went to space? To see the milky way!" The man, impressed, thanks the farmer and asks, "How did you manage to teach the cow to tell jokes?" The farmer smiles and says, "Oh, that's easy. You just have to make sure she always has a captivated audience. After all, who doesn't love good farm stories?" The man laughs, thanks the farmer again, and goes on his way, thinking that it was the most surreal and amusing experience he's ever had.

#29 opened 7 months ago by

New activity in latent-consistency/super-fast-lcm-lora-sd1.5 12 months ago

Alternative to Triton?

#1 opened 12 months ago by

New activity in HuggingFaceM4/VLM_WebSight_finetuned 12 months ago

Training details?

#6 opened 12 months ago by

New activity in latent-consistency/lcm-lora-sdv1-5 about 1 year ago

Failed to match keys when loading network lcm-lora-sdv1-5.safetensors

#2 opened about 1 year ago by

New activity in latent-consistency/lcm-ssd-1b about 1 year ago

Result not good

#4 opened about 1 year ago by

New activity in Xenova/whisper-web about 1 year ago

Source maps 😇?

#10 opened about 1 year ago by

New activity in lmz/candle-whisper about 1 year ago

Conversion guide

#1 opened about 1 year ago by

New activity in radames/Real-Time-Latent-Consistency-Model about 1 year ago

Black screen on M1

#8 opened about 1 year ago by

New activity in stabilityai/stable-video-diffusion-img2vid-xt about 1 year ago

FYI: SVD-XT: Same architecture as SVD but finetuned for 25 frame generation.

#6 opened about 1 year ago by

New activity in CompVis/stable-diffusion-v-1-4-original about 2 years ago

Access Request

#236 opened about 2 years ago by