issues
search
ReaLLMASIC
/
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
MIT License
23
stars
17
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Add first association maps
#199
klei22
opened
1 month ago
0
Add support for Audio Tokenization and Voice Emulation via SNAC Tokenization
#198
klei22
closed
1 month ago
0
Add wte factorization
#197
klei22
opened
1 month ago
1
Add scripts compatible with the Newswire Dataset
#196
klei22
closed
1 month ago
0
a draft of gated attention and its modification
#195
Hrancheng
opened
1 month ago
0
golden gen for decoder
#194
Buck008
closed
1 month ago
3
Add nan handling strategy for run_vizier.py
#193
klei22
opened
2 months ago
0
Add quantized krmsnorm
#192
klei22
closed
1 month ago
3
Rubiks cube improvements
#191
klei22
closed
2 months ago
1
Add matrix factorization and visuals
#190
klei22
opened
2 months ago
1
Add linear wrapper and kan feedback
#189
klei22
closed
2 months ago
1
Remove duplicate block in model.py
#188
gkielian
closed
2 months ago
0
Add scripts creating compatibility for additional dataset
#187
klei22
closed
2 months ago
0
Add vizier optimization
#186
klei22
closed
2 months ago
0
added core_array code and activation function code
#185
zymeng3001
opened
2 months ago
0
Quantization and Binarization Implementations for Linear Layers
#184
mmoffatt2
closed
1 week ago
3
Add scripts compatible with Zyda and FineWeb-Edu pre-training datasets
#183
klei22
closed
2 months ago
0
Add kan and hyperparams
#182
gkielian
closed
2 months ago
4
try of implementing cross-layer attention
#181
Hrancheng
opened
2 months ago
4
Add hardware component verilog from tapeout repo
#180
zymeng3001
closed
2 months ago
0
Add embedding table factorization
#179
klei22
opened
2 months ago
1
Add Option for Memory Optimized Training via Gradient Checkpointing
#178
klei22
closed
2 months ago
1
Add settings log, graphs, and model augmentation to sample.py
#177
klei22
closed
2 months ago
0
Add and improve scripts for dataset processing
#176
klei22
closed
3 months ago
1
Add template for parquet datasets
#175
klei22
closed
3 months ago
0
Added boxplots
#174
mmoffatt2
closed
3 months ago
1
replace linear with KAN
#173
SenmiaoORZ
closed
2 months ago
3
Add interactivity to sample.py
#172
klei22
closed
3 months ago
0
Fixed typo in consmax_sweep config
#171
karthik-sunil
closed
3 months ago
0
Add fix for torchrun multigpu training
#170
gkielian
closed
3 months ago
0
Add dim to init functions for softmax variations
#169
gkielian
closed
3 months ago
0
Add option to use SwiGLU FFN Option
#168
gkielian
closed
3 months ago
0
Softmax parameter sweep
#167
karthik-sunil
closed
3 months ago
1
Softmax formulation pass
#166
gkielian
closed
3 months ago
1
merged with master and enabled plotting of strongermax/polymax
#165
Hrancheng
closed
3 months ago
0
Make n_kv_group 6 by default to enable flash attn
#164
gkielian
closed
3 months ago
0
Modified train.py to enable plotting of input/output statistics for constantmax
#163
Hrancheng
closed
3 months ago
1
Add Softplus activation and update inspect script
#162
gkielian
closed
3 months ago
0
Add scripts compatible wtih the korean parallel corpora
#161
klei22
closed
3 months ago
0
Fix non euler base calculation for exppolymax
#160
gkielian
closed
4 months ago
0
Add polymax with relu2 forward pass (PolymaxQuan)
#159
gkielian
closed
3 months ago
1
Add scripts for testing out-of-distribution addition
#158
klei22
closed
4 months ago
0
Add scripts compatible with lichess dataset
#157
klei22
closed
3 months ago
0
Tidy implementation
#156
gkielian
closed
4 months ago
1
Add softmax variation dictionary
#155
gkielian
closed
4 months ago
0
Quest: Add chess dataset for chess bot
#154
gkielian
closed
3 months ago
1
Add partial RMSnorm "pRMSNorm" variation
#153
gkielian
closed
4 months ago
1
Add table customization
#152
gkielian
closed
4 months ago
1
Add checkpoint inspector
#151
gkielian
closed
4 months ago
0
Add vector tokenization
#150
gkielian
opened
4 months ago
0
Previous
Next