Create devcontainer.json #367
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Add a symlink for llama_models * Update README.md paths
…ig -> model_config (meta-llama#225)
Updated model card to remove erroneous heading markdown in Hardware and Software section
…RLs (meta-llama#244) * Model should work with "raw" bytes, never URLs Modeling code or code close to it (chat_format.py specifically) should not be thinking of downloading URLs, etc. Especially not doing it randomly on-demand. * Use ModelInputMessage / ModelOutputMessage and BytesIO * Fixes * Fold everything into a much simpler RawMessage type, update prompt_format
…meta-llama#255) * Test PR Submission - Write Permission * Update EFS volume structuring * Test cron scheduling * Schedule cron job and update branch inputs / actions versioning * Remove previous temporary unnecessary commit lines
Signed-off-by: Dmitry Rogozhkin <[email protected]>
…a-llama#256) * models nightly * publish * environment * schedule * test manual trigger * fix * name * test * test manual input * move back to workflow * dev * dev * workflow_dispatch
* refactor: make llama3 and llama4 generation closer to each other * llama3 script fixes * fixes * add llama3 quant * fix * fix * fix * fix * fix * fix * fix * fix * fix * resurrect xpu codepath * update readme
…hiding of python_start, python_end
Fixes: b12e462 ("refactor: make llama3 generation closer to llama4 (meta-llama#309)") Signed-off-by: Dmitry Rogozhkin <[email protected]>
Verified with Llama3.2-3B-Instruct on Intel Data Center Max Series GPU (PVC): ``` torchrun --nproc-per-node=1 models/llama3/scripts/completion.py \ "$CHECKPOINT_DIR" --world_size 1 torchrun --nproc-per-node=1 models/llama3/scripts/chat_completion.py \ "$CHECKPOINT_DIR" --world_size 1 ``` Signed-off-by: Dmitry Rogozhkin <[email protected]>
Pytorch xccl distributed backend is available starting from 2.7 (requires manual build of pytorch with `USE_C10D_XCCL=1 USE_XCCL=1`) and is targeted for inclusion in binary builds starting from 2.8. This patch improves support of visual llama3 model on XPU devices and tested with `Llama3.2-11B-Vision-Instruct`. Signed-off-by: Dmitry Rogozhkin <[email protected]>
…snorm, name it as such (meta-llama#320)
* fix: update rope scaling for Llama-4-Scout * update * no defaults * fix
``` PYTHONPATH=$(git rev-parse --show-toplevel) \ torchrun --nproc_per_node=1 \ -m models.llama4.scripts.chat_completion ../checkpoints/Llama-4-Scout-17B-16E-Instruct \ --world_size 1 \ --quantization-mode int4_mixed ``` Before this PR: ``` [rank1]: TypeError: quantize_int4() got multiple values for argument 'output_device' ```
# What does this PR do? ## Test Plan
# What does this PR do? ## Test Plan
Making a test run see what happens
Cnp11784
requested review from
ashwinb,
dltn,
ehhuang,
hardikjshah,
raghotham and
yanxi0830
as code owners
|
Hi @Cnp11784! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at [email protected]. Thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Making a test run see what happens