Viktor Ferenczi
viktor-ferenczi
AI & ML interests
AI tools for software development, program search, genetic algorithms
Recent Activity
liked
a model
14 days ago
casperhansen/deepseek-r1-distill-llama-70b-awq
liked
a model
14 days ago
casperhansen/deepseek-r1-distill-qwen-32b-awq
liked
a model
15 days ago
deepseek-ai/DeepSeek-R1
Organizations
None yet
viktor-ferenczi's activity
Context length?
10
#2 opened about 1 year ago
by
turboderp
EOS fine-tuning
2
#1 opened about 1 year ago
by
viktor-ferenczi
Any plans for YaRN CodeLlama?
3
#6 opened over 1 year ago
by
viktor-ferenczi
Is the custom configuration still required?
#1 opened over 1 year ago
by
viktor-ferenczi
Smaller variant
1
#3 opened over 1 year ago
by
viktor-ferenczi
Empty model card
1
#2 opened over 1 year ago
by
viktor-ferenczi
rope_theta
#6 opened over 1 year ago
by
viktor-ferenczi
llama2-chat-70b-w4 weights
2
#1 opened over 1 year ago
by
sandrobovelli
Update `README.md`
3
#1 opened over 1 year ago
by
alvarobartt
How to prompt the model properly?
#16 opened over 1 year ago
by
viktor-ferenczi
Error loading model into Test Generation Web UI (ooba)
8
#11 opened over 1 year ago
by
viktor-ferenczi
What hardware do I need for reasonable performance?
4
#3 opened over 1 year ago
by
TS0001
Is the snippet in README loading the model in 8-bit mode?
5
#2 opened over 1 year ago
by
mahmoudajawad
How does the embedding model on code text?
4
#18 opened over 1 year ago
by
chonghao-cc
Coding test runs into a loop
#10 opened over 1 year ago
by
viktor-ferenczi
Experience
1
#18 opened over 1 year ago
by
viktor-ferenczi
Can't run model
5
#1 opened over 1 year ago
by
mikeytrw