issues
search
alan-turing-institute
/
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
MIT License
1
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Group query attention implementation
#13
rchan26
closed
2 weeks ago
1
Improve KV cache by allowing it to extend to larger sequence lengths
#12
rchan26
opened
3 weeks ago
0
Extend to working with batches of variable length prompts
#11
rchan26
opened
3 weeks ago
0
Add KV cache option for inference
#10
rchan26
closed
3 weeks ago
2
Fork set up
#9
rchan26
closed
3 weeks ago
1
Add different activation functions
#8
rchan26
opened
1 month ago
0
Add PEFT fine tuning
#7
llewelld
opened
1 month ago
0
GPT2 in pure C/CUDA
#6
llewelld
opened
1 month ago
1
Explore quantisation techniques
#5
rchan26
opened
1 month ago
0
Use different position embeddings
#4
rchan26
opened
1 month ago
0
Add different attention mechisms
#3
rchan26
opened
1 month ago
0
Extend to training on multiple GPUs
#2
rchan26
opened
1 month ago
1
Add KV-caching to inference
#1
rchan26
closed
3 weeks ago
2