maywell commited on
Commit
b3a407d
β€’
1 Parent(s): 6e66d1f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md CHANGED
@@ -1,3 +1,78 @@
1
  ---
 
 
 
 
 
2
  license: cc-by-nc-4.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - ko
4
+
5
+ library_name: transformers
6
+ pipeline_tag: text-generation
7
  license: cc-by-nc-4.0
8
  ---
9
+
10
+ # **Synatra-V0.2-7B**
11
+
12
+ Made by StableFluffy
13
+
14
+ [Visit my website! - Currently on consturction..](https://www.stablefluffy.kr/)
15
+
16
+ [Join Discord Server](https://discord.gg/HTUBtvjUZa)
17
+
18
+ ## License
19
+
20
+ This model is strictly [*non-commercial*](https://creativecommons.org/licenses/by-nc/4.0/) (**cc-by-nc-4.0**) use only which takes priority over the **LLAMA 2 COMMUNITY LICENSE AGREEMENT**.
21
+ The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included **cc-by-nc-4.0** license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences.
22
+ The licence can be changed after new model released.
23
+
24
+ ## Model Details
25
+ **Base Model**
26
+ [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
27
+
28
+ **Trained On**
29
+ A6000 48GB * 8
30
+
31
+ ## Instruction format
32
+
33
+ In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
34
+
35
+ E.g.
36
+ ```
37
+ text = "<s>[INST] μ•„μ΄μž‘ λ‰΄ν„΄μ˜ 업적을 μ•Œλ €μ€˜. [/INST]"
38
+ ```
39
+
40
+ # **Model Benchmark**
41
+
42
+ Preparing...
43
+
44
+ # **Implementation Code**
45
+
46
+ Since, chat_template already contains insturction format above.
47
+ You can use the code below.
48
+
49
+ ```python
50
+ from transformers import AutoModelForCausalLM, AutoTokenizer
51
+
52
+ device = "cuda" # the device to load the model onto
53
+
54
+ model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-V0.1-7B")
55
+ tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-V0.1-7B")
56
+
57
+ messages = [
58
+ {"role": "user", "content": "What is your favourite condiment?"},
59
+ ]
60
+
61
+ encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
62
+
63
+ model_inputs = encodeds.to(device)
64
+ model.to(device)
65
+
66
+ generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
67
+ decoded = tokenizer.batch_decode(generated_ids)
68
+ print(decoded[0])
69
+ ```
70
+
71
+ If you run it on oobabooga your prompt would look like this.
72
+ ```
73
+ [INST] 링컨에 λŒ€ν•΄μ„œ μ•Œλ €μ€˜. [/INST]
74
+ ```
75
+
76
+ > Readme format: [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b)
77
+
78
+ ---