mlabonne commited on
Commit
86aa556
·
verified ·
1 Parent(s): 03a51b7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -136,11 +136,13 @@ What is the current status of candidate ID 12345?<|im_end|>
136
  <|im_start|>assistant
137
  <|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
138
  <|im_start|>tool
139
- <|tool_response_start|>{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}<|tool_response_end|><|im_end|>
140
  <|im_start|>assistant
141
  The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>
142
  ```
143
 
 
 
144
  **Architecture**: Hybrid model with multiplicative gates and short convolutions: 18 double-gated short-range LIV convolution blocks and 6 grouped query attention (GQA) blocks.
145
 
146
  **Pre-training mixture**: Approximately 75% English, 20% multilingual, and 5% code data sourced from the web and licensed materials.
 
136
  <|im_start|>assistant
137
  <|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
138
  <|im_start|>tool
139
+ <|tool_response_start|>[{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}]<|tool_response_end|><|im_end|>
140
  <|im_start|>assistant
141
  The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>
142
  ```
143
 
144
+ You can directly pass tools as JSON schema or Python functions with `.apply_chat_template()` as shown in [this page](https://huggingface.co/docs/transformers/en/chat_extras) to automatically format the system prompt.
145
+
146
  **Architecture**: Hybrid model with multiplicative gates and short convolutions: 18 double-gated short-range LIV convolution blocks and 6 grouped query attention (GQA) blocks.
147
 
148
  **Pre-training mixture**: Approximately 75% English, 20% multilingual, and 5% code data sourced from the web and licensed materials.