john smith

kth8's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in deepseek-ai/DeepSeek-R1 4 days ago

Request: Create distill of Mistral Small 24B

2

#128 opened 4 days ago by

Kenshiro-28

New activity in deepseek-ai/DeepSeek-R1 10 days ago

Hardware requirements?

27

#19 opened 21 days ago by

JohnnieB

New activity in bartowski/granite-3.0-8b-instruct-GGUF 4 months ago

Continuous output

8

#1 opened 4 months ago by

kth8

New activity in meta-llama/Llama-3.2-3B-Instruct 4 months ago

MMLU-Pro benchmark

5

#13 opened 5 months ago by

kth8

New activity in ggerganov/whisper.cpp 4 months ago

Add large-v3-turbo model

6

#17 opened 4 months ago by

kth8

New activity in meta-llama/Llama-3.2-1B-Instruct 5 months ago

MMLU-Pro benchmark

#16 opened 5 months ago by

kth8

New activity in HF1BitLLM/Llama3-8B-1.58-100B-tokens 5 months ago

GGUF conversion

11

#3 opened 5 months ago by

compilade

liked a model 5 months ago

terrycraddock/Reflection-Llama-3.1-8B

Text Generation • Updated Sep 14, 2024 • 3.11k • 16

New activity in mattshumer/Reflection-Llama-3.1-70B 5 months ago

The 8B Version Works Better

2

#44 opened 5 months ago by

gr0010

CORRECTION: THIS SYSTEM MESSAGE IS ***PURE GOLD***!!!

16

#33 opened 5 months ago by

jukofyork