Hugging Face's logo
John Leimgruber III's picture
33 8 117

John Leimgruber III

ubergarm
21world's profile picture Andhika1996's profile picture tensiondriven's profile picture
·
https://emptyduck.com

AI & ML interests

Open LLMs and Astrophotography image processing.

Recent Activity

new activity 5 days ago
unsloth/DeepSeek-R1-GGUF:No think tokens visible
new activity 6 days ago
unsloth/DeepSeek-R1-GGUF:Over 2 tok/sec agg backed by NVMe SSD on 96GB RAM + 24GB VRAM AM5 rig with llama.cpp
upvoted an article 6 days ago
Open-R1: a fully open reproduction of DeepSeek-R1
View all activity

Organizations

None yet

ubergarm's activity

New activity in unsloth/DeepSeek-R1-GGUF 5 days ago

No think tokens visible

4
#15 opened 6 days ago by
sudkamath
New activity in unsloth/DeepSeek-R1-GGUF 6 days ago

Over 2 tok/sec agg backed by NVMe SSD on 96GB RAM + 24GB VRAM AM5 rig with llama.cpp

9
#13 opened 7 days ago by
ubergarm
New activity in unsloth/DeepSeek-R1-GGUF 7 days ago

Got it running after downloading some RAM!

4
#7 opened 8 days ago by
ubergarm
New activity in mradermacher/Qwen2.5-14B-Instruct-1M-i1-GGUF 7 days ago

Over 128k context on 1x 3090 TI FE 24GB VRAM!
#1 opened 7 days ago by
ubergarm
New activity in unsloth/DeepSeek-R1-GGUF 7 days ago

Inference speed

2
#9 opened 8 days ago by
Iker
New activity in HKUSTAudio/Llasa-3B 9 days ago

Control over output

1
#12 opened 10 days ago by
TeachableMachine
New activity in srinivasbilla/llasa-3b-tts 10 days ago

Emotions

2
#3 opened 11 days ago by
jujutechnology
New activity in jinaai/ReaderLM-v2 15 days ago

What advantage does this have over normal algorithmic ways of turning HTML to Markdown ?

5
#5 opened 20 days ago by
MohamedRashad
New activity in bartowski/DeepSeek-R1-Distill-Llama-70B-GGUF 16 days ago

FuseO1-DeekSeekR1-QwQ-SkyT1-32B-Preview

2
#1 opened 16 days ago by
AaronFeng753
New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-32B 16 days ago

System Prompt

17
#2 opened 17 days ago by
Wanfq
New activity in bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF 16 days ago

FIXED: Error with llama-server `unknown pre-tokenizer type: 'deepseek-r1-qwen'`

4
#1 opened 16 days ago by
ubergarm
New activity in unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit 16 days ago

The `tokenizer_config.json` is missing the `chat_template` jinja?

1
#1 opened 16 days ago by
ubergarm
New activity in LatitudeGames/Wayfarer-12B-GGUF 20 days ago

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

2
#2 opened 20 days ago by
ubergarm
New activity in hexgrad/Kokoro-82M about 1 month ago

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

5
#20 opened about 1 month ago by
ubergarm
New activity in bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF 4 months ago

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

12
#2 opened 4 months ago by
ThePabli
New activity in bartowski/SuperNova-Medius-GGUF 4 months ago

63.17 MMLU-Pro Computer Science with `Q8_0`
#2 opened 4 months ago by
ubergarm
New activity in bartowski/qwen2.5-7b-ins-v3-GGUF 4 months ago

Benchmarks worse than Qwen2.5-7B-Instruct on MMLU-Pro Computer Science in limited testing.
#1 opened 4 months ago by
ubergarm
New activity in bartowski/Qwen2.5-32B-Instruct-GGUF 4 months ago

Promising looking results on 24GB VRAM folks!

9
#3 opened 5 months ago by
ubergarm
New activity in deepseek-ai/DeepSeek-V2.5 5 months ago

Awesome model

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

vram usage of each?

3
#1 opened 5 months ago by
jasonden