Hugging Face's logo
John Leimgruber III's picture
16 4 69

John Leimgruber III

ubergarm
21world's profile picture
·
https://emptyduck.com

AI & ML interests

Open LLMs and Astrophotography image processing.

Organizations

None yet

ubergarm's activity

New activity in bartowski/Qwen2.5-32B-Instruct-GGUF 9 days ago

Promising looking results on 24GB VRAM folks!

5
#3 opened 15 days ago by ubergarm
New activity in deepseek-ai/DeepSeek-V2.5 17 days ago

Awesome model

6
#5 opened 26 days ago by dillfrescott
New activity in bartowski/DeepSeek-V2.5-GGUF 20 days ago

vram usage of each?

3
#1 opened 23 days ago by jasonden
New activity in bartowski/Mistral-Large-Instruct-2407-GGUF 2 months ago

Works good generating python on my 64GB RAM w/ 3090TI 24GB VRAM dev box

3
#2 opened 2 months ago by ubergarm

Chat template

3
#3 opened 2 months ago by sydneyfong

Can you please provide the command to change the context size?

5
#1 opened 2 months ago by yehiaserag
New activity in qwp4w3hyb/Meta-Llama-3.1-8B-Instruct-iMat-GGUF 2 months ago

The first GGUF that works with long context on llama.cpp!

3
#1 opened 2 months ago by ubergarm
New activity in MaziyarPanahi/Mistral-Nemo-Instruct-2407-GGUF 3 months ago

And where is the GGUF file itself?

12
#1 opened 3 months ago by Anonimus12345678902
New activity in CompendiumLabs/mistral-nemo-instruct-2407-gguf 3 months ago

Got it working in llama.cpp! Thanks!

1
#1 opened 3 months ago by ubergarm
New activity in QuantFactory/Mistral-Nemo-Instruct-2407-GGUF 3 months ago

Error loading model in llama.cpp ?

8
#1 opened 3 months ago by ubergarm
New activity in gradientai/Llama-3-70B-Instruct-Gradient-262k 4 months ago

Prompt Format

4
#6 opened 5 months ago by JamesConley
New activity in OpenGVLab/InternVL-Chat-V1-5 5 months ago

Quantized model coming?

8
#3 opened 6 months ago by dnhkng
New activity in failspy/InternVL-Chat-V1-5-4bit 5 months ago

Output is empty

2
#3 opened 5 months ago by bingw5
New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 5 months ago

~8 tok/sec with ~5k context on vLLM with Flash Attention and `kv_cache_dtype="fp8"` on 3090TI 24GB VRAM

2
#2 opened 5 months ago by ubergarm
New activity in MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF 5 months ago

The f16 with 32k ctx fits nicely in 24GB VRAM

5
#3 opened 5 months ago by ubergarm
New activity in stabilityai/stable-cascade 8 months ago

AttributeError: 'generator' object has no attribute 'image_embeddings'

1
#26 opened 8 months ago by MohamedRashad