aashish1904 commited on
Commit
ac026e1
·
verified ·
1 Parent(s): dd52f7e

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ license: apache-2.0
5
+ pipeline_tag: text-generation
6
+ language:
7
+ - ja
8
+ - en
9
+ tags:
10
+ - japanese
11
+ - mistral
12
+ inference: false
13
+ base_model: mistralai/Mistral-Nemo-Base-2407
14
+
15
+ ---
16
+
17
+ ![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
18
+
19
+ # QuantFactory/Mistral-Nemo-Japanese-Instruct-2408-GGUF
20
+ This is quantized version of [cyberagent/Mistral-Nemo-Japanese-Instruct-2408](https://huggingface.co/cyberagent/Mistral-Nemo-Japanese-Instruct-2408) created using llama.cpp
21
+
22
+ # Original Model Card
23
+
24
+ # Mistral-Nemo-Japanese-Instruct-2408
25
+
26
+ ## Model Description
27
+
28
+ This is a Japanese continually pre-trained model based on [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407).
29
+
30
+ ## Usage
31
+
32
+ Make sure to update your transformers installation via `pip install --upgrade transformers`.
33
+
34
+ ```python
35
+ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
36
+
37
+ model = AutoModelForCausalLM.from_pretrained("cyberagent/Mistral-Nemo-Japanese-Instruct-2408", device_map="auto", torch_dtype="auto")
38
+ tokenizer = AutoTokenizer.from_pretrained("cyberagent/Mistral-Nemo-Japanese-Instruct-2408")
39
+ streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
40
+
41
+ messages = [
42
+ {"role": "system", "content": "あなたは親切なAIアシスタントです。"},
43
+ {"role": "user", "content": "AIによって私たちの暮らしはどのように変わりますか?"}
44
+ ]
45
+
46
+ input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
47
+ output_ids = model.generate(input_ids,
48
+ max_new_tokens=1024,
49
+ temperature=0.5,
50
+ streamer=streamer)
51
+ ```
52
+
53
+ ## Prompt Format
54
+ ChatML Format
55
+ ```
56
+ <s><|im_start|>system
57
+ あなたは親切なAIアシスタントです。<|im_end|>
58
+ <|im_start|>user
59
+ AIによって私たちの暮らしはどのように変わりますか?<|im_end|>
60
+ <|im_start|>assistant
61
+
62
+
63
+ ```
64
+
65
+ ## License
66
+ Apache-2.0
67
+
68
+ ## Author
69
+
70
+ [Ryosuke Ishigami](https://huggingface.co/rishigami)
71
+
72
+ ## How to cite
73
+
74
+ ```tex
75
+ @misc{cyberagent-mistral-nemo-japanese-instruct-2408,
76
+ title={Mistral-Nemo-Japanese-Instruct-2408},
77
+ url={https://huggingface.co/cyberagent/Mistral-Nemo-Japanese-Instruct-2408},
78
+ author={Ryosuke Ishigami},
79
+ year={2024},
80
+ }
81
+ ```