Skip to content
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

Support Llama3.1-nemotron-70b-inst-hf #2299

Merged
merged 11 commits into from
Oct 21, 2024
Merged

Support Llama3.1-nemotron-70b-inst-hf #2299

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
618eaaa
add transformers in gitignore
DaozeZhang Sep 10, 2024
8fd4051
fix a typo bug in text-caps
DaozeZhang Sep 11, 2024
f7a3eea
Merge branch 'modelscope:main' into main
DaozeZhang Sep 20, 2024
add49e5
add .run into gitignore
DaozeZhang Sep 20, 2024
4f43621
Merge commit 'f7a3eeaf0c57a100e985276fa783239f21fa9ee6'
DaozeZhang Sep 20, 2024
40d3ad0
add vlmeval to gitignore
DaozeZhang Sep 30, 2024
a3ae3ca
Merge commit '9bae58c9dc3015855bcd6a75794eb9c3947cb476'
DaozeZhang Sep 30, 2024
818d0fd
add my_model/ to gitignore
DaozeZhang Oct 18, 2024
619a4bd
Merge commit '704381f2e27b29c94b97b7c12d1e8a2dd886fdff'
DaozeZhang Oct 18, 2024
604d429
support llama3.1-nemotron-70b-inst-hf
DaozeZhang Oct 21, 2024
a2e75d8
Merge commit '39494b774b6fc3dec042b1d17935b3fa5cd6b46d' into llama3.1…
DaozeZhang Oct 21, 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
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ benchmarks/
eval_outputs/
transformers/
vlmeval/
my_model/
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please try not to change this file

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

git用得还不太好，sorry


# Pytorch
*.pth
Expand Down
1 change: 1 addition & 0 deletions docs/source/Instruction/支持的模型和数据集.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,6 +199,7 @@
|llama3_1-405b-instruct-awq|[LLM-Research/Meta-Llama-3.1-405B-Instruct-AWQ-INT4](https://modelscope.cn/models/LLM-Research/Meta-Llama-3.1-405B-Instruct-AWQ-INT4/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✔|✘|transformers>=4.43, autoawq|-|[hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4)|
|llama3_1-405b-instruct-gptq-int4|[LLM-Research/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4](https://modelscope.cn/models/LLM-Research/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✘|✘|transformers>=4.43, auto_gptq|-|[hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4)|
|llama3_1-405b-instruct-bnb|[LLM-Research/Meta-Llama-3.1-405B-Instruct-BNB-NF4](https://modelscope.cn/models/LLM-Research/Meta-Llama-3.1-405B-Instruct-BNB-NF4/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✘|✘|transformers>=4.43, bitsandbytes|-|[hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4)|
|llama-3.1-nemotron-70B-instruct-hf|[AI-ModelScope/Llama-3.1-Nemotron-70B-Instruct-HF](https://modelscope.cn/models/AI-ModelScope/Llama-3.1-Nemotron-70B-Instruct-HF/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✔|✘|transformers>=4.43|-|[nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF)|
|llama3_2-1b|[LLM-Research/Llama-3.2-1B](https://modelscope.cn/models/LLM-Research/Llama-3.2-1B/summary)|q_proj, k_proj, v_proj|default-generation|✔|✔|✔|✘|transformers>=4.45|-|[meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)|
|llama3_2-1b-instruct|[LLM-Research/Llama-3.2-1B-Instruct](https://modelscope.cn/models/LLM-Research/Llama-3.2-1B-Instruct/summary)|q_proj, k_proj, v_proj|llama3_2|✔|✔|✔|✘|transformers>=4.45|-|[meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)|
|llama3_2-3b|[LLM-Research/Llama-3.2-3B](https://modelscope.cn/models/LLM-Research/Llama-3.2-3B/summary)|q_proj, k_proj, v_proj|default-generation|✔|✔|✔|✘|transformers>=4.45|-|[meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)|
Expand Down
1 change: 1 addition & 0 deletions docs/source_en/Instruction/Supported-models-datasets.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,6 +199,7 @@ The table below introcudes all models supported by SWIFT:
|llama3_1-405b-instruct-awq|[LLM-Research/Meta-Llama-3.1-405B-Instruct-AWQ-INT4](https://modelscope.cn/models/LLM-Research/Meta-Llama-3.1-405B-Instruct-AWQ-INT4/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✔|✘|transformers>=4.43, autoawq|-|[hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4)|
|llama3_1-405b-instruct-gptq-int4|[LLM-Research/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4](https://modelscope.cn/models/LLM-Research/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✘|✘|transformers>=4.43, auto_gptq|-|[hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4)|
|llama3_1-405b-instruct-bnb|[LLM-Research/Meta-Llama-3.1-405B-Instruct-BNB-NF4](https://modelscope.cn/models/LLM-Research/Meta-Llama-3.1-405B-Instruct-BNB-NF4/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✘|✘|transformers>=4.43, bitsandbytes|-|[hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4)|
|llama-3.1-nemotron-70B-instruct-hf|[AI-ModelScope/Llama-3.1-Nemotron-70B-Instruct-HF](https://modelscope.cn/models/AI-ModelScope/Llama-3.1-Nemotron-70B-Instruct-HF/summary)|q_proj, k_proj, v_proj|llama3|✔|✔|✔|✘|transformers>=4.43|-|[nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF)|
|llama3_2-1b|[LLM-Research/Llama-3.2-1B](https://modelscope.cn/models/LLM-Research/Llama-3.2-1B/summary)|q_proj, k_proj, v_proj|default-generation|✔|✔|✔|✘|transformers>=4.45|-|[meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)|
|llama3_2-1b-instruct|[LLM-Research/Llama-3.2-1B-Instruct](https://modelscope.cn/models/LLM-Research/Llama-3.2-1B-Instruct/summary)|q_proj, k_proj, v_proj|llama3_2|✔|✔|✔|✘|transformers>=4.45|-|[meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)|
|llama3_2-3b|[LLM-Research/Llama-3.2-3B](https://modelscope.cn/models/LLM-Research/Llama-3.2-3B/summary)|q_proj, k_proj, v_proj|default-generation|✔|✔|✔|✘|transformers>=4.45|-|[meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)|
Expand Down
13 changes: 13 additions & 0 deletions swift/llm/utils/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,6 +261,8 @@ class ModelType:
llama3_1_405b_instruct_awq = 'llama3_1-405b-instruct-awq'
llama3_1_405b_instruct_gptq_int4 = 'llama3_1-405b-instruct-gptq-int4'
llama3_1_405b_instruct_bnb = 'llama3_1-405b-instruct-bnb'
# llama3.1-nemotron
llama3_1_nemotron_70B_instruct_hf = 'llama-3.1-nemotron-70B-instruct-hf'
# llama3.2
llama3_2_1b = 'llama3_2-1b'
llama3_2_1b_instruct = 'llama3_2-1b-instruct'
Expand Down Expand Up @@ -4892,6 +4894,17 @@ def get_model_tokenizer_deepseek_vl(model_dir: str,
return model, tokenizer


@register_model(
ModelType.llama3_1_nemotron_70B_instruct_hf,
'AI-ModelScope/Llama-3.1-Nemotron-70B-Instruct-HF',
LoRATM.llama,
TemplateType.llama3,
support_flash_attn=True,
support_vllm=True,
support_lmdeploy=True,
requires=['transformers>=4.43'],
ignore_file_pattern=[r'.+\.pth$'],
hf_model_id='nvidia/Llama-3.1-Nemotron-70B-Instruct-HF')
@register_model(
ModelType.openbuddy_llama3_1_8b_chat,
'OpenBuddy/openbuddy-llama3.1-8b-v22.1-131k',
Expand Down
Loading