Rickard Edén
neph1
AI & ML interests
applying, dataset creation, finetuning, loras
Recent Activity
updated
a model
7 days ago
neph1/Qwen2.5-Coder-7B-Instruct-Unity
liked
a model
10 days ago
deepseek-ai/deepseek-coder-6.7b-base
Organizations
neph1's activity
Great work!
5
#2 opened about 1 month ago
by
dollarpound
Thank you!
1
#1 opened about 1 month ago
by
neph1
This looks amazing
3
#1 opened about 1 month ago
by
neph1
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
Librarian Bot: Add language metadata for dataset
#3 opened 3 months ago
by
librarian-bot
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
good luck!
6
#2 opened 3 months ago
by
mradermacher
functional?
#1 opened 5 months ago
by
neph1
Safetensors?
1
#3 opened 8 months ago
by
mo137
Smaller IQs performance?
2
#1 opened 8 months ago
by
neph1
3B version?
4
#1 opened 10 months ago
by
Chriffe
fp32 for everything?
2
#8 opened 10 months ago
by
neph1
Running a 4-bit Quantized 7B Model on a PC: Feasibility and Insights
4
#109 opened 10 months ago
by
edw-hug-face
I'd like to see a GGUF version of this
3
#5 opened 10 months ago
by
iplayfast
Unquantized version
#2 opened 10 months ago
by
neph1
[bot] Conversion to Parquet
#1 opened 11 months ago
by
parquet-converter
Q6_K appears to be broken (And maybe other K-Quants as well)
3
#11 opened 12 months ago
by
Mikael110
Why is the response slower than the 70B model?
7
#9 opened 12 months ago
by
shalene
chatbot giving weird responses
20
#6 opened 12 months ago
by
hammad93
[bot] Conversion to Parquet
#1 opened about 1 year ago
by
parquet-converter