root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Updated Templates supported by llama_chat_apply_template (markdown)

Xuan Son Nguyen 2024-04-19 17:11:12 +02:00
parent 643ffe9cbb
commit 9b85bc0f62
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Templates-supported-by-llama_chat_apply_template.md

@ -138,6 +138,12 @@ CohereForAI/c4ai-command-r-plus
<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are a helpful assistant<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>Hi there<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Who are you<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>I am an assistant<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Another question<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
```
```
Usage: ./server -m ... --chat-template llama3
meta-llama/Meta-Llama-3-8B-Instruct
<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nHi there<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWho are you<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nI am an assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nAnother question<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n
```
Additionally, we also support zephyr template (I cannot find it on huggingface, but have seen in [this list](https://github.com/ggerganov/llama.cpp/blob/c8d847d57efdc0f9bbbf881d48c645e151b36fd8/examples/server/public/promptFormats.js) )
```