John Leimgruber III's picture

John Leimgruber III

ubergarm

·

https://emptyduck.com

ubergarm

AI & ML interests

Open LLMs and Astrophotography image processing.

Recent Activity

liked a model about 9 hours ago

jinaai/ReaderLM-v2

new activity about 13 hours ago

LatitudeGames/Wayfarer-12B-GGUF:Great RP model in only 12B! A few notes and sampler settings for llama.cpp server inside.

liked a model 1 day ago

LatitudeGames/Wayfarer-12B

View all activity

Organizations

None yet

ubergarm's activity

New activity in LatitudeGames/Wayfarer-12B-GGUF about 13 hours ago

Great RP model in only 12B! A few notes and sampler settings for llama.cpp server inside.

#2 opened about 13 hours ago by

New activity in hexgrad/Kokoro-82M 12 days ago

Nice ~90x real-time generation on 3090TI. Quickstart provided.

#20 opened 12 days ago by

New activity in bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF 3 months ago

Observation: 4-bit quantization can't answer the Strawberry prompt

#2 opened 3 months ago by

New activity in bartowski/SuperNova-Medius-GGUF 3 months ago

63.17 MMLU-Pro Computer Science with `Q8_0`

#2 opened 3 months ago by

New activity in bartowski/qwen2.5-7b-ins-v3-GGUF 3 months ago

Benchmarks worse than Qwen2.5-7B-Instruct on MMLU-Pro Computer Science in limited testing.

#1 opened 3 months ago by

New activity in bartowski/Qwen2.5-32B-Instruct-GGUF 4 months ago

Promising looking results on 24GB VRAM folks!

#3 opened 4 months ago by

New activity in deepseek-ai/DeepSeek-V2.5 4 months ago

Awesome model

#5 opened 4 months ago by

New activity in bartowski/DeepSeek-V2.5-GGUF 4 months ago

vram usage of each?

#1 opened 4 months ago by

New activity in bartowski/Mistral-Large-Instruct-2407-GGUF 6 months ago

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

#2 opened 6 months ago by

Chat template

#3 opened 6 months ago by

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

#1 opened 6 months ago by

New activity in qwp4w3hyb/Meta-Llama-3.1-8B-Instruct-iMat-GGUF 6 months ago

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

#1 opened 6 months ago by

New activity in MaziyarPanahi/Mistral-Nemo-Instruct-2407-GGUF 6 months ago

And where is the GGUF file itself?

#1 opened 6 months ago by

Anonimus12345678902

New activity in CompendiumLabs/mistral-nemo-instruct-2407-gguf 6 months ago

Got it working in llama.cpp! Thanks!

#1 opened 6 months ago by

New activity in QuantFactory/Mistral-Nemo-Instruct-2407-GGUF 6 months ago

Error loading model in llama.cpp ?

#1 opened 6 months ago by

New activity in gradientai/Llama-3-70B-Instruct-Gradient-262k 8 months ago

Prompt Format

#6 opened 9 months ago by

New activity in OpenGVLab/InternVL-Chat-V1-5 8 months ago

Quantized model coming?

#3 opened 9 months ago by

New activity in failspy/InternVL-Chat-V1-5-4bit 8 months ago

Output is empty

#3 opened 8 months ago by

New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 9 months ago

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

#2 opened 9 months ago by

New activity in MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF 9 months ago

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

#3 opened 9 months ago by