Upload README.md
Browse files
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
inference: false
|
7 |
+
tags:
|
8 |
+
- transformers
|
9 |
+
- gguf
|
10 |
+
- imatrix
|
11 |
+
- openchat-3.5-0106
|
12 |
+
---
|
13 |
+
Quantizations of https://huggingface.co/openchat/openchat-3.5-0106
|
14 |
+
|
15 |
+
# From original readme
|
16 |
+
|
17 |
+
### Conversation templates
|
18 |
+
|
19 |
+
💡 **Default Mode (GPT4 Correct)**: Best for coding, chat and general tasks
|
20 |
+
|
21 |
+
```
|
22 |
+
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:
|
23 |
+
```
|
24 |
+
|
25 |
+
🧮 **Mathematical Reasoning Mode**: Tailored for solving math problems
|
26 |
+
|
27 |
+
```
|
28 |
+
Math Correct User: 10.3 − 7988.8133=<|end_of_turn|>Math Correct Assistant:
|
29 |
+
```
|
30 |
+
|
31 |
+
⚠️ **Notice:** Remember to set `<|end_of_turn|>` as end of generation token.
|
32 |
+
|
33 |
+
The default (GPT4 Correct) template is also available as the integrated `tokenizer.chat_template`,
|
34 |
+
which can be used instead of manually specifying the template:
|
35 |
+
|
36 |
+
```python
|
37 |
+
messages = [
|
38 |
+
{"role": "user", "content": "Hello"},
|
39 |
+
{"role": "assistant", "content": "Hi"},
|
40 |
+
{"role": "user", "content": "How are you today?"}
|
41 |
+
]
|
42 |
+
tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
|
43 |
+
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]
|
44 |
+
```
|
45 |
+
```
|