duyntnet's picture
Upload README.md
9aaa1c4 verified
|
raw
history blame
1.42 kB
---
license: other
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- transformers
- gguf
- imatrix
- openchat-3.5-0106
---
Quantizations of https://huggingface.co/openchat/openchat-3.5-0106
# From original readme
### Conversation templates
💡 **Default Mode (GPT4 Correct)**: Best for coding, chat and general tasks
```
GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:
```
🧮 **Mathematical Reasoning Mode**: Tailored for solving math problems
```
Math Correct User: 10.3 − 7988.8133=<|end_of_turn|>Math Correct Assistant:
```
⚠️ **Notice:** Remember to set `<|end_of_turn|>` as end of generation token.
The default (GPT4 Correct) template is also available as the integrated `tokenizer.chat_template`,
which can be used instead of manually specifying the template:
```python
messages = [
{"role": "user", "content": "Hello"},
{"role": "assistant", "content": "Hi"},
{"role": "user", "content": "How are you today?"}
]
tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
```
```