Add LLaMAv2-70B text generation #441
Merged
Conversation
This file contains 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
Update README with performance optimal command for LLaMAv2-70B text generation using deepspeed
|
The documentation is not available anymore as the PR was closed or merged. |
regisss
reviewed
Oct 3, 2023
examples/text-generation/README.md
Outdated
| @@ -95,6 +95,11 @@ python ../gaudi_spawn.py --use_deepspeed --world_size 8 run_generation.py \ | |||
| --max_new_tokens 100 | |||
| ``` | |||
|
|
|||
| Text generation with LLaMAv2-70B model(using deepspeed) can be done using the following command: | |||
| ```bash | |||
| python ../gaudi_spawn.py --use_deepspeed --world_size 8 run_generation.py --model_name_or_path <MODEL_PATH>/Llama-2-70b-hf/ --max_new_tokens 4096 --bf16 --use_hpu_graphs --use_kv_cache --batch_size 56 --attn_softmax_bf16 --limit_hpu_graphs --n_iterations 5 --reuse_cache --trim_logits | |||
There was a problem hiding this comment.
Suggested change
| python ../gaudi_spawn.py --use_deepspeed --world_size 8 run_generation.py --model_name_or_path <MODEL_PATH>/Llama-2-70b-hf/ --max_new_tokens 4096 --bf16 --use_hpu_graphs --use_kv_cache --batch_size 56 --attn_softmax_bf16 --limit_hpu_graphs --n_iterations 5 --reuse_cache --trim_logits | |
| python ../gaudi_spawn.py --use_deepspeed --world_size 8 run_generation.py \ | |
| --model_name_or_path meta-llama/Llama-2-70b-hf \ | |
| --max_new_tokens 4096 \ | |
| --bf16 \ | |
| --use_hpu_graphs \ | |
| --use_kv_cache \ | |
| --batch_size 56 \ | |
| --attn_softmax_bf16 \ | |
| --limit_hpu_graphs \ | |
| --reuse_cache \ | |
| --trim_logits |
regisss
reviewed
Oct 3, 2023
regisss
added
run-test
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Update README with performance optimal command for LLaMAv2-70B text generation using deepspeed
What does this PR do?
Add LLaMAv2-70B text generation commands to README
Fixes # (issue)
Before submitting