Michael PRO
michaelfeil
AI & ML interests
ML Inference
Recent Activity
new activity
about 3 hours ago
voyageai/voyage-4-nano:NIT Update config.json
new activity
about 4 hours ago
voyageai/voyage-4-nano:framework support via use_bidirectional_attention - Cheers from your friends at Baseten
updated
a model
1 day ago
baseten/embedding-smol_llama-101M-GQA
Organizations
NIT Update config.json
1
#4 opened about 3 hours ago
by
michaelfeil
framework support via use_bidirectional_attention - Cheers from your friends at Baseten
1
#3 opened about 4 hours ago
by
michaelfeil
"use_bidirectional_attention": true flag
#13 opened 2 days ago
by
michaelfeil
dummy config.json
#26 opened 4 days ago
by
michaelfeil
missing tokenizer
#3 opened 2 months ago
by
michaelfeil
Update chat_template.jinja
#1 opened 4 months ago
by
baseten-admin
Set CTX Length to 2048
2
#19 opened 4 months ago
by
michaelfeil
moonshotai/Kimi-K2-Instruct-0905
#4638 opened 5 months ago
by
michaelfeil
Update config.json
2
#130 opened 5 months ago
by
michaelfeil
remove-tiktoken
🔥
1
3
#1 opened 6 months ago
by
bdubayah
Update usage with infinity
4
#36 opened about 1 year ago
by
michaelfeil
Missing weights in architecture
👀
1
2
#2 opened 6 months ago
by
m-ric
Add-huggingface-tokenizer
👍
10
#24 opened 6 months ago
by
michaelfeil
add regular tokenizer
👀
👍
5
2
#8 opened 8 months ago
by
michaelfeil
Cite this Repo
👍
1
#10 opened 7 months ago
by
michaelfeil
GGUF?
1
#1 opened 7 months ago
by
PonderosaSharon
Differences compared to the original models
1
#1 opened 8 months ago
by
tomaarsen
Question on converting this to DeepSeekV2ForCausalLM
1
#2 opened 8 months ago
by
michaelfeil
Max positional embeddings in readme is 40k, here is 32k
#2 opened 8 months ago
by
michaelfeil
vLLM support
🔥
4
4
#1 opened 8 months ago
by
ccdv