Giters
karpathy
/
llama2.c
Inference Llama 2 in one file of pure C
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
16203
Watchers:
183
Issues:
212
Forks:
1852
karpathy/llama2.c Issues
Everyone, I have implemented multi-token prediction of InfiniAttention and meta.
Updated
2 days ago
Comments count
1
Training Tiny Stories: 'CUDA' -vs- 'MPS'
Updated
3 days ago
Comments count
2
Simplified llama2.c.dll
Updated
4 days ago
Comments count
4
Can this be compiled to run on Windows 10, or Windows XP?
Updated
4 days ago
Comments count
3
Not an issue: Asking for help
Closed
5 days ago
Comments count
2
support for SIMD in matmul might increase performance i think so...
Closed
6 days ago
Comments count
1
mmap failed! ./run llama2_7b_q80.bin
Updated
6 days ago
Everyone, I have implemented multi-token prediction of InfiniAttention and meta.
Updated
7 days ago
runomp on Mac M1 Max is slower than runfast
Updated
10 days ago
Comments count
10
-O3 does not apply auto-vectorization on X86-64 CPU
Updated
10 days ago
Comments count
1
the export model and read_checkpoint is conflict
Updated
10 days ago
Comments count
2
Tokenizer errors out when inferencing llama2
Updated
10 days ago
Comments count
1
malloc failed! on stories260 model
Updated
10 days ago
Comments count
1
How about Llama3?
Closed
25 days ago
Comments count
1
Plans C (compromised iOS devices, apologies not me)
Closed
a month ago
Can the Huggingface model be converted to ckpt.pt to support training?
Updated
a month ago
Could llama2.c be adapted to BitNet?
Updated
2 months ago
RuntimeError with CUDA assertion failure when resuming model training from checkpoint
Updated
2 months ago
Comments count
1
add feature: export (quantize) from Llama2.c format
Updated
2 months ago
Once upon a time, there was a little girl named Lily
Updated
2 months ago
Comments count
5
Runing llama2.c on a microcontroller
Updated
2 months ago
Comments count
1
Can you make a sora (diffusion transformer) tutorial similar to llama2.c?
Updated
2 months ago
Comments count
1
[Suggestion] Enable Discussion
Updated
3 months ago
Comments count
1
I'm doing an experiment with image generation, but my script outputs a binary file, how can I train a model using llama2.c?
Closed
3 months ago
Could anyone port deepseek-moe to llama2.c?
Updated
3 months ago
Please implement a project
Closed
3 months ago
New Visual Walkthrough of Llama2.c
Updated
3 months ago
Mobile React native Support Ported
Updated
3 months ago
Understanding "multiple_of"
Updated
3 months ago
Train/val split
Updated
3 months ago
Code/script to reproduce val loss using the shared models
Updated
3 months ago
Comments count
3
How to quantize stories15M.bin
Closed
4 months ago
Comments count
1
can i train on cpu
Updated
4 months ago
Comments count
5
Significant Quality Degradation with q8 Quantization in Small Models
Updated
4 months ago
Comments count
4
HOw to add different coropus ?
Updated
4 months ago
Comments count
4
Keras based tiny llama implementations
Updated
4 months ago
casual attention implementation
Closed
4 months ago
Comments count
3
How do we reproduce your stories, by a more practical Q&A chat model?
Updated
4 months ago
Comments count
1
Llama-shepherd-cli a small tool to keep track of implementations in various languages
Updated
4 months ago
NanoGPT in c for inference
Closed
5 months ago
export does not seem to work?
Closed
5 months ago
Comments count
2
mfu calculation
Updated
5 months ago
Is it possible to use Orca2 with this code ?
Updated
5 months ago
Comments count
1
numpy llama2 for fun and learning
Closed
6 months ago
ld: warning: ignoring duplicate libraries: '-lgcc'
Updated
6 months ago
How to train a chat model
Updated
6 months ago
Prefill Processing
Updated
6 months ago
Comments count
2
Llama transformer walkthrough
Updated
6 months ago
How to run interface on GPU
Updated
7 months ago
can the custom model in llama2.c format be exported to hf format?
Updated
7 months ago
Comments count
1
Previous
Next