Skip to content

Add int8 models to Llama2 and Llama3 #1734

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
merged 2 commits into from
Aug 6, 2024
Merged

Add int8 models to Llama2 and Llama3 #1734

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
48b199e
Add int8 models
james77777778 Aug 5, 2024
61d1a5d
Update llama's descriptions
james77777778 Aug 6, 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
38 changes: 35 additions & 3 deletions keras_nlp/src/models/llama/llama_presets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,27 +17,59 @@
backbone_presets = {
"llama2_7b_en": {
"metadata": {
"description": "LLaMA 2 7B Base model",
"description": "7 billion parameter, 32-layer, base LLaMA 2 model.",
"params": 6738415616,
"official_name": "LLaMA 2",
"path": "llama2",
"model_card": "https://github.com/meta-llama/llama",
},
"kaggle_handle": "kaggle://keras/llama2/keras/llama2_7b_en/1",
},
"llama2_7b_en_int8": {
"metadata": {
"description": (
"7 billion parameter, 32-layer, base LLaMA 2 model with "
"activation and weights quantized to int8."
),
"params": 6739839488,
"official_name": "LLaMA 2",
"path": "llama2",
"model_card": "https://github.com/meta-llama/llama",
},
"kaggle_handle": "kaggle://keras/llama2/keras/llama2_7b_en_int8/1",
},
"llama2_instruct_7b_en": {
"metadata": {
"description": "LLaMA 2 7B Chat model",
"description": (
"7 billion parameter, 32-layer, instruction tuned LLaMA 2 "
"model."
),
"params": 6738415616,
"official_name": "LLaMA 2",
"path": "llama2",
"model_card": "https://github.com/meta-llama/llama",
},
"kaggle_handle": "kaggle://keras/llama2/keras/llama2_instruct_7b_en/1",
},
"llama2_instruct_7b_en_int8": {
"metadata": {
"description": (
"7 billion parameter, 32-layer, instruction tuned LLaMA 2 "
"model with activation and weights quantized to int8."
),
"params": 6739839488,
"official_name": "LLaMA 2",
"path": "llama2",
"model_card": "https://github.com/meta-llama/llama",
},
"kaggle_handle": "kaggle://keras/llama2/keras/llama2_instruct_7b_en_int8/1",
},
"vicuna_1.5_7b_en": {
"metadata": {
"description": "Vicuna v1.5 7B Chat model",
"description": (
"7 billion parameter, 32-layer, instruction tuned Vicuna v1.5 "
"model."
),
"params": 6738415616,
"official_name": "Vicuna",
"path": "vicuna",
Expand Down
35 changes: 33 additions & 2 deletions keras_nlp/src/models/llama3/llama3_presets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,22 +17,53 @@
backbone_presets = {
"llama3_8b_en": {
"metadata": {
"description": "LLaMA 3 8B Base model",
"description": "8 billion parameter, 32-layer, base LLaMA 3 model.",
"params": 8030261248,
"official_name": "LLaMA 3",
"path": "llama3",
"model_card": "https://github.com/meta-llama/llama3",
},
"kaggle_handle": "kaggle://keras/llama3/keras/llama3_8b_en/3",
},
"llama3_8b_en_int8": {
"metadata": {
"description": (
"8 billion parameter, 32-layer, base LLaMA 3 model with "
"activation and weights quantized to int8."
),
"params": 8031894016,
"official_name": "LLaMA 3",
"path": "llama3",
"model_card": "https://github.com/meta-llama/llama3",
},
"kaggle_handle": "kaggle://keras/llama3/keras/llama3_8b_en_int8/1",
},
"llama3_instruct_8b_en": {
"metadata": {
"description": "LLaMA 3 8B Instruct model",
"description": (
"8 billion parameter, 32-layer, instruction tuned LLaMA 3 "
"model."
),
"params": 8030261248,
"official_name": "LLaMA 3",
"path": "llama3",
"model_card": "https://github.com/meta-llama/llama3",
},
"kaggle_handle": "kaggle://keras/llama3/keras/llama3_instruct_8b_en/3",
},
"llama3_instruct_8b_en_int8": {
"metadata": {
"description": (
"8 billion parameter, 32-layer, instruction tuned LLaMA 3 "
"model with activation and weights quantized to int8."
),
"params": 8031894016,
"official_name": "LLaMA 3",
"path": "llama3",
"model_card": "https://github.com/meta-llama/llama3",
},
"kaggle_handle": (
"kaggle://keras/llama3/keras/llama3_instruct_8b_en_int8/1"
),
},
}