Skip to content

Pull requests: karpathy/llama2.c

New pull request New
40 Open 265 Closed
40 Open 265 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add another Rust port
#521 opened May 12, 2024 by code-cp Loading…
Add llama3.c port to README.md
#514 opened Apr 29, 2024 by jameswdelancey Loading…
Windows _fseeki64 _ftelli64 bug fix to load LLaMA2 7B >4GB weight
#513 opened Apr 27, 2024 by jameswdelancey Loading…
1
Use int instead of float to calculate weights_ptr
#512 opened Apr 27, 2024 by qianzhangxa Loading…
2
Optional verbose output argument & printing of params. & their values.
#511 opened Apr 26, 2024 by RhinoDevel Loading…
Add llama2.cpp implementation link to readme
#509 opened Apr 20, 2024 by AmeyaWagh Loading…
fix: Define loop index i before usage
#504 opened Apr 13, 2024 by Keycatowo Loading…
Update export.py
#503 opened Apr 11, 2024 by eltociear Loading…
add link to fork llama2Rnn.c
#498 opened Mar 20, 2024 by siyuanseever Loading…
[README] add a Rust port of this project with GPU support
#494 opened Mar 4, 2024 by oliverhu Loading…
Initialize Tokenizer and simplify str_lookup prototype
#491 opened Feb 25, 2024 by pagakarthik Loading…
Add a dependenices check
#487 opened Feb 22, 2024 by BarrettBytes Loading…
fixed dimension comments in RunState
#486 opened Feb 22, 2024 by rupnikj Loading…
fix allocation of scaling factors
#459 opened Dec 9, 2023 by moritztng Loading…
2
Loading HF models with num_attention_heads != num_key_value_heads
#436 opened Oct 25, 2023 by fwtan Loading…
Support GQA export, better run.c, Support tinyllama-1.1B high-priority
#410 opened Sep 27, 2023 by magician-blue Loading…
7
export and run with bfloat16 weight matrices
#407 opened Sep 25, 2023 by efocht Loading…
Simple float CUDA port
#376 opened Sep 2, 2023 by rogerallen Loading…
6
Ref: move train files to train directory
#361 opened Aug 26, 2023 by madroidmaq Loading…
1
Extract dataset functionality for easy extensibility
#360 opened Aug 26, 2023 by alxkolm Loading…
implementin an Engine to serve the trained model by inferencing
#359 opened Aug 26, 2023 by Majdoddin • Draft
3
Patch to avoid useless logits computation
#351 opened Aug 24, 2023 by rdentato Loading…
export model to fp16
#347 opened Aug 23, 2023 by kroggen Loading…
9
Modified export.py to add the ability to export fp16 weights.
#345 opened Aug 23, 2023 by rdentato Loading…
6
Training: save train config to config.json
#333 opened Aug 21, 2023 by madroidmaq Loading…
ProTip! Filter pull requests by the default branch with base:master.