Hugging Face's logo
Yuki Sasaki's picture
13 7 17

Yuki Sasaki

yumemio
21world's profile picture
·
https://www.yumem.io

AI & ML interests

Smart agriculture, geo-sensing, LLM evaluation

Organizations

None yet

yumemio's activity

New activity in mattshumer/ref_70_e3 11 days ago

Weight diff visualization

2
#4 opened 11 days ago by yumemio
New activity in gpt-omni/mini-omni 15 days ago

Multi-turn voice conversations

2
#3 opened 16 days ago by yumemio
New activity in mistralai/Mistral-Large-Instruct-2407 about 1 month ago

Does the "Average Generation Length" in the press release mean the average number of output tokens?
#20 opened about 1 month ago by yumemio
New activity in microsoft/Phi-3-small-128k-instruct about 2 months ago

Target_module of this phi-3-small model

10
#3 opened 4 months ago by hackint0sh
New activity in ai21labs/Jamba-v0.1 about 2 months ago

Fast Mamba

5
#34 opened 6 months ago by Praneethkeerthi
New activity in bartowski/gemma-2-27b-it-GGUF 3 months ago

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma2'

4
#1 opened 3 months ago by cloudyu
New activity in google/gemma-2-27b-it 3 months ago

Citation URL redirects to Gemma-1

1
#8 opened 3 months ago by yumemio
New activity in grapevine-AI/stockmark-100b-instruct-v0.1-gguf 3 months ago

Warning message: "GENERATION QUALITY WILL BE DEGRADED! CONSIDER REGENERATING THE MODEL"

2
#1 opened 4 months ago by yumemio
commented a paper 4 months ago
New activity in stockmark/stockmark-100b-instruct-v0.1 4 months ago

KeyError when running the sample code snippet
#2 opened 4 months ago by yumemio
New activity in apple/OpenELM 4 months ago

MMLU is 25?????

2
#3 opened 5 months ago by sleepyjoecheated
New activity in microsoft/Phi-3-small-128k-instruct 4 months ago

`<|endoftext|>` in other model variants

2
#6 opened 4 months ago by yumemio
New activity in tokyotech-llm/Swallow-7b-instruct-v0.1 5 months ago

Typo in the system prompt example?

2
#1 opened 5 months ago by yumemio