Vasile Ermicioi
vasilee
AI & ML interests
typescript, graphql, algorithms, machine learning
Recent Activity
liked
a model
3 days ago
tiiuae/Falcon-H1-7B-Instruct-GGUF
liked
a model
3 days ago
mistralai/Devstral-Small-2505
liked
a model
3 days ago
tiiuae/Falcon-H1-3B-Instruct-GGUF
Organizations
None yet
vasilee's activity
this model/quant is generating bad output
1
#1 opened 7 months ago
by
vasilee
Technical requirement to use NuExtract-v1.5
6
#5 opened 7 months ago
by
radema
is it available to change output text format to Markdown?
10
#21 opened 8 months ago
by
MhmdSyd

Running on llama.cpp
🤝
3
5
#2 opened 10 months ago
by
YvonF

please add LLama3 prefix to the model name as required by llama3 license
👍
2
3
#2 opened 11 months ago
by
vasilee
error loading model: create_tensor: tensor 'output.weight' not found ?
6
#1 opened over 1 year ago
by
wukongai
How to quantize these models?
8
#2 opened over 1 year ago
by
supercharge19
so whats the hypothesis?
👍
4
7
#2 opened over 1 year ago
by
fblgit

llama.cpp is working fine with the models
#1 opened over 1 year ago
by
vasilee
finetuning from GGUF format?
8
#2 opened over 1 year ago
by
vasilee
Illegal instruction with llama_cpp_python-0.2.11
2
#1 opened over 1 year ago
by
vasilee
dolphin-2.1-mistral-7B is even better than openorca-mistral-7b unbelievable
👍
5
5
#1 opened over 1 year ago
by
mirek190
Is the dataset public?
2
#4 opened over 1 year ago
by
luiscosio
Synthia-7B-v1.3.q4_k_s.gguf doesn't work
1
#2 opened over 1 year ago
by
vasilee
GGUF model?
1
#4 opened over 1 year ago
by
vasilee
Hi what did you train this model with, and what were hyperparams?
7
#1 opened over 1 year ago
by
teknium

bug? example of usage?
4
#1 opened almost 2 years ago
by
vasilee
Weights license
11
#2 opened almost 2 years ago
by
DhanOS

remove repetitive models from the leaderboard
1
#14 opened almost 2 years ago
by
vasilee