Update README.md
Browse files
README.md
CHANGED
|
@@ -135,11 +135,13 @@ What is the current status of candidate ID 12345?<|im_end|>
|
|
| 135 |
<|im_start|>assistant
|
| 136 |
<|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
|
| 137 |
<|im_start|>tool
|
| 138 |
-
<|tool_response_start|>{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}<|tool_response_end|><|im_end|>
|
| 139 |
<|im_start|>assistant
|
| 140 |
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|>
|
| 141 |
```
|
| 142 |
|
|
|
|
|
|
|
| 143 |
**Architecture**: Hybrid model with multiplicative gates and short convolutions: 10 double-gated short-range LIV convolution blocks and 6 grouped query attention (GQA) blocks.
|
| 144 |
|
| 145 |
**Pre-training mixture**: Approximately 75% English, 20% multilingual, and 5% code data sourced from the web and licensed materials.
|
|
|
|
| 135 |
<|im_start|>assistant
|
| 136 |
<|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
|
| 137 |
<|im_start|>tool
|
| 138 |
+
<|tool_response_start|>[{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}]<|tool_response_end|><|im_end|>
|
| 139 |
<|im_start|>assistant
|
| 140 |
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|>
|
| 141 |
```
|
| 142 |
|
| 143 |
+
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.
|
| 144 |
+
|
| 145 |
**Architecture**: Hybrid model with multiplicative gates and short convolutions: 10 double-gated short-range LIV convolution blocks and 6 grouped query attention (GQA) blocks.
|
| 146 |
|
| 147 |
**Pre-training mixture**: Approximately 75% English, 20% multilingual, and 5% code data sourced from the web and licensed materials.
|