israel commited on
Commit
e444f01
·
verified ·
1 Parent(s): 354bf01

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -4
README.md CHANGED
@@ -10,9 +10,9 @@ tags:
10
  - sft
11
  - generated_from_trainer
12
  datasets:
13
- - israel/sd
14
  model-index:
15
- - name: zephyr-7b-gemma-sft-alpaca
16
  results: []
17
  language:
18
  - af
@@ -27,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # zephyr-7b-gemma-sft-alpaca
29
 
30
- This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the israel/sd dataset.
31
  It achieves the following results on the evaluation set:
32
  - Loss: 0.2737
33
 
@@ -76,4 +76,39 @@ The following hyperparameters were used during training:
76
  - Transformers 4.39.0.dev0
77
  - Pytorch 2.2.1+cu121
78
  - Datasets 2.14.6
79
- - Tokenizers 0.15.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  - sft
11
  - generated_from_trainer
12
  datasets:
13
+ - masakhane/african-translated-alpaca
14
  model-index:
15
+ - name: zephyr-7b-gemma-sft-african-alpaca
16
  results: []
17
  language:
18
  - af
 
27
 
28
  # zephyr-7b-gemma-sft-alpaca
29
 
30
+ This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the masakhane/african-translated-alpaca dataset.
31
  It achieves the following results on the evaluation set:
32
  - Loss: 0.2737
33
 
 
76
  - Transformers 4.39.0.dev0
77
  - Pytorch 2.2.1+cu121
78
  - Datasets 2.14.6
79
+ - Tokenizers 0.15.2
80
+
81
+
82
+
83
+
84
+ ### Usage
85
+
86
+ ```python
87
+
88
+ # Install transformers from source - only needed for versions <= v4.34
89
+ # pip install git+https://github.com/huggingface/transformers.git
90
+ # pip install accelerate
91
+
92
+ import torch
93
+ from transformers import pipeline
94
+
95
+ pipe = pipeline("text-generation", model="israel/zephyr-7b-gemma-sft-alpaca", torch_dtype=torch.bfloat16, device_map="auto")
96
+
97
+ # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
98
+ messages = [
99
+ {
100
+ "role": "system",
101
+ "content": "You are a friendly chatbot who answewrs question in given language",
102
+ },
103
+ {"role": "user", "content": "what is the 3 biggest countrys in Africa?"},
104
+ ]
105
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
106
+ outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
107
+ print(outputs[0]["generated_text"])
108
+ # <|system|>
109
+ # You are a friendly chatbot who always responds in the style of a pirate<eos>
110
+ # <|user|>
111
+ # what is the 3 biggest countrys in Africa?<eos>
112
+ # <|assistant|>
113
+ # The 3 biggest countries in Africa are Nigeria, Ethiopia and South Africa.
114
+ ```