Skip to content

Add Llama 3 models #501

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yunfeng-scale merged 2 commits into from
Apr 24, 2024
Merged

Add Llama 3 models #501

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0ce8198
Add Llama 3 models
yunfeng-scale Apr 24, 2024
30b4d80
fix
yunfeng-scale Apr 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions docs/model_zoo.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,10 @@ Scale hosts the following models in the LLM Engine Model Zoo:
| `llama-2-13b-chat` | ✅ | | text-generation-inference, vllm | 4096 |
| `llama-2-70b` | ✅ | ✅ | text-generation-inference, vllm | 4096 |
| `llama-2-70b-chat` | ✅ | | text-generation-inference, vllm | 4096 |
| `llama-3-8b` | ✅ | | vllm | 8192 |
| `llama-3-8b-instruct` | ✅ | | vllm | 8192 |
| `llama-3-70b` | ✅ | | vllm | 8192 |
| `llama-3-70b-instruct` | ✅ | | vllm | 8192 |
| `falcon-7b` | ✅ | | text-generation-inference, vllm | 2048 |
| `falcon-7b-instruct` | ✅ | | text-generation-inference, vllm | 2048 |
| `falcon-40b` | ✅ | | text-generation-inference, vllm | 2048 |
Expand Down
5 changes: 5 additions & 0 deletions model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,6 +162,10 @@
"llama-2-13b-chat",
"llama-2-70b",
"llama-2-70b-chat",
"llama-3-8b",
"llama-3-8b-instruct",
"llama-3-70b",
"llama-3-70b-instruct",
"falcon-7b",
"falcon-7b-instruct",
"falcon-40b",
Expand Down Expand Up @@ -231,6 +235,7 @@
# Can also see 13B, 34B there too
"gemma": {"max_model_len": 8192, "max_num_batched_tokens": 8192},
"llama-2": {"max_model_len": None, "max_num_batched_tokens": 4096},
"llama-3": {"max_model_len": None, "max_num_batched_tokens": 8192},
"mistral": {"max_model_len": 8000, "max_num_batched_tokens": 8000},
"mixtral-8x7b": {"max_model_len": 32768, "max_num_batched_tokens": 32768},
"mixtral-8x22b": {"max_model_len": 65536, "max_num_batched_tokens": 65536},
Expand Down
4 changes: 4 additions & 0 deletions model-engine/model_engine_server/infra/repositories/live_tokenizer_repository.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,10 @@ def get_default_supported_models_info() -> Dict[str, ModelInfo]:
"llama-2-13b-chat": ModelInfo("meta-llama/Llama-2-13b-chat-hf", None),
"llama-2-70b": ModelInfo("meta-llama/Llama-2-70b-hf", None),
"llama-2-70b-chat": ModelInfo("meta-llama/Llama-2-70b-chat-hf", None),
"llama-3-8b": ModelInfo("meta-llama/Meta-Llama-3-8B", None),
"llama-3-8b-instruct": ModelInfo("meta-llama/Meta-Llama-3-8B-Instruct", None),
"llama-3-70b": ModelInfo("meta-llama/Meta-Llama-3-70B", None),
"llama-3-70b-instruct": ModelInfo("meta-llama/Meta-Llama-3-70B-Instruct", None),
"falcon-7b": ModelInfo("tiiuae/falcon-7b", None),
"falcon-7b-instruct": ModelInfo("tiiuae/falcon-7b-instruct", None),
"falcon-40b": ModelInfo("tiiuae/falcon-40b", None),
Expand Down