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

Add 01-ai/Yi-1.5-34B-Chat #1145

Merged
merged 3 commits into from
May 15, 2024
Merged

Add 01-ai/Yi-1.5-34B-Chat #1145

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5a44287
Add 01-ai/Yi-1.5-34B-Chat
mishig25 May 15, 2024
c336882
change positioning
mishig25 May 15, 2024
8f93ae5
Merge branch 'main' into add_yi
May 15, 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
31 changes: 30 additions & 1 deletion chart/env/prod.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,36 @@ envVars:
"stop": ["<|im_end|>"]
}
},
{
{
"name": "01-ai/Yi-1.5-34B-Chat",
"tokenizer": "01-ai/Yi-1.5-34B-Chat",
"description" : "Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.",
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/01-ai-logo.png",
"modelUrl": "https://huggingface.co/01-ai/Yi-1.5-34B-Chat",
"websiteUrl": "https://www.01.ai",
"preprompt": "",
"chatPromptTemplate": "{{preprompt}}{{#each messages}}{{#ifUser}}<|im_start|>user\\n{{content}}<|im_end|>\\n<|im_start|>assistant\\n{{/ifUser}}{{#ifAssistant}}{{content}}<|im_end|>{{/ifAssistant}}{{/each}}",
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

converted this jinja to handlebars https://huggingface.co/01-ai/Yi-1.5-34B-Chat/blob/main/tokenizer_config.json#L40

Copy link
Collaborator

Choose a reason for hiding this comment

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

I removed this, since we can load the chat prompt template from the tokenizer_config.json directly, the model was acting strange with this custom chat template. (internal discussion)

Copy link
Collaborator

Choose a reason for hiding this comment

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

commit

"parameters": {
"stop": ["<|im_end|>"],
"temperature": 0.3,
"max_new_tokens": 1024,
"truncate": 1000,
"top_p": 0.8,
Comment on lines +184 to +189
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

copied from https://huggingface.co/spaces/01-ai/Yi-1.5-34B-Chat/blob/main/.env.local.template#L28-L34

},
"promptExamples": [
{
"title": "Write an email from bullet list",
"prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
}, {
"title": "Code a snake game",
"prompt": "Code a basic snake game in python, give explanations for each step."
}, {
"title": "Assist in a task",
"prompt": "How do I make a delicious lemon cheesecake?"
}
]
},
{
"name" : "google/gemma-1.1-7b-it",
"description": "Gemma 7B 1.1 is the latest release in the Gemma family of lightweight models built by Google, trained using a novel RLHF method.",
"websiteUrl" : "https://blog.google/technology/developers/gemma-open-models/",
Expand Down
Loading