Michael PRO
michaelfeil
AI & ML interests
ML Inference
Recent Activity
liked
a model
3 days ago
michaelfeil/Qwen3-Embedding-8B-auto
new activity
12 days ago
mistralai/Devstral-Small-2505:add regular tokenizer
updated
a model
13 days ago
baseten/btest-Qwen-0.5B-NVIDIA-H100-80GB-HBM3-v0.20.0-TP1
Organizations
add regular tokenizer
👀
👍
5
2
#8 opened about 2 months ago
by
michaelfeil
Cite this Repo
#10 opened 17 days ago
by
michaelfeil
GGUF?
1
#1 opened 20 days ago
by
PonderosaSharon
Differences compared to the original models
1
#1 opened 29 days ago
by
tomaarsen
Question on converting this to DeepSeekV2ForCausalLM
1
#2 opened 26 days ago
by
michaelfeil
Max positional embeddings in readme is 40k, here is 32k
#2 opened about 1 month ago
by
michaelfeil
vLLM support
🔥
3
3
#1 opened about 1 month ago
by
ccdv
Add last token pooling
❤️
1
1
#2 opened about 1 month ago
by
michaelfeil
Automatically add EOS via Tokenizer, integrate Sentence Transformers
1
#1 opened about 1 month ago
by
tomaarsen
Update config.json
#28 opened about 1 month ago
by
michaelfeil
Add configuration deepseek
👍
3
#50 opened about 1 month ago
by
michaelfeil
Please add the missing `configuration_deepseek.py` file
👍
3
3
#14 opened about 1 month ago
by
abeatkuzco
HF Tokenizers support
👍
👀
8
#7 opened about 2 months ago
by
michaelfeil
Update config.json
#27 opened about 2 months ago
by
michaelfeil
make model generate think tag
#13 opened about 2 months ago
by
michaelfeil
Update config.json
#12 opened 2 months ago
by
michaelfeil
Context length?
13
#2 opened over 1 year ago
by
turboderp
Merged colqwen2.5-v0.2 model
#5 opened 3 months ago
by
michaelfeil
Serverless API
2
#1 opened 5 months ago
by
alexanderniebuhr
