wbag's picture

wbag

Walmart-the-bag

AI & ML interests

Merging, Finetuning, and Pretraining LLM models.

Recent Activity

Organizations

Blog-explorers's profile picture ZeroGPU Explorers's profile picture Replete-AI's profile picture MLX Community's profile picture Social Post Explorers's profile picture Dev Mode Explorers's profile picture head_empty ai's profile picture Skye Team's profile picture Unofficial HuggingChat Plugins's profile picture llmcompressor-quants's profile picture

Walmart-the-bag's activity

posted an update 2 months ago
reacted to merve's post with šŸš€ 2 months ago
view post
Post
2844
This is not a drill šŸ’„
HuggingChat is now multimodal with meta-llama/Llama-3.2-11B-Vision-Instruct! šŸ¤—
This also comes with multimodal assistants, I have migrated my Marcus Aurelius advice assistant to Llama-Vision and Marcus can see now! šŸ˜„

Chat with Marcus: https://hf.co/chat/assistant/65bfed22022ba290531112f8
Start chatting with Llama-Vision 3.2 11B Instruct https://huggingface.co/chat/models/meta-llama/Llama-3.2-11B-Vision-Instruct
  • 1 reply
Ā·
reacted to KingNish's post with šŸ‘ 3 months ago
replied to KingNish's post 7 months ago
view reply

The vision model is pretty good. šŸ¤£
image.png

reacted to KingNish's post with āž• 7 months ago
view post
Post
4632
Microsoft Just Launched 3 Powerful Models

1. Phi 3 Medium (4k and 128k): A 14b Instruct tuned models that outperformed big models like Command R+ (104b), GPT 3.5 Pro, Gemini Pro, and is highly competitive with top models such as Mixtral 8x22b, Llama3 70B, and GPT 4.
microsoft/Phi-3-medium-4k-instruct
DEMO: https://huggingface.co/spaces/Walmart-the-bag/Phi-3-Medium

2. Phi 3 Mini Vision 128k: A 4.5 billion-parameter, instruction-tuned vision model that has outperformed models such as Llava3 and Claude 3, and is providing stiff competition to Gemini 1Pro Vision.
microsoft/Phi-3-vision-128k-instruct

3. Phi3 Small (8k and 128k): Better than Llama3 8b, Mixtral 8x7b and GPT 3.5 turbo.
microsoft/Phi-3-small-128k-instruct
Ā·
posted an update 7 months ago
posted an update 7 months ago
posted an update 8 months ago
posted an update 8 months ago
view post
Post
1058
Replete-AI/code_bagel


Make the ultimate coding finetune to compete with the likes of closed source models using the code_bagel dataset!

Made by @rombodawg of RepleteAi, the code_bagel dataset contains over 800 million tokens of deduplicated and uncensored code from only reputable sources on huggingface. This code is formatted in the alpaca instruct format for ease of use in training.
replied to merve's post 8 months ago
replied to victor's post 11 months ago