Tianduo commited on
Commit
d51e57c
•
1 Parent(s): 221ac31

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - cerebras/SlimPajama-627B
5
+ - bigcode/starcoderdata
6
+ - OpenAssistant/oasst_top1_2023-08-25
7
+ language:
8
+ - en
9
+ ---
10
+ <div align="center">
11
+
12
+ # TinyLlama-1.1B
13
+ </div>
14
+
15
+ https://github.com/jzhang38/TinyLlama
16
+
17
+ The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
18
+
19
+
20
+ We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
21
+
22
+ #### This Model
23
+ This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T).
24
+ The dataset used is [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25) following the [chatml](https://github.com/openai/openai-python/blob/main/chatml.md) format.
25
+ #### How to use
26
+ You will need the transformers>=4.31
27
+ Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
28
+ ```
29
+ from transformers import AutoTokenizer
30
+ import transformers
31
+ import torch
32
+ model = "PY007/TinyLlama-1.1B-Chat-v0.4"
33
+ tokenizer = AutoTokenizer.from_pretrained(model)
34
+ pipeline = transformers.pipeline(
35
+ "text-generation",
36
+ model=model,
37
+ torch_dtype=torch.float16,
38
+ device_map="auto",
39
+ )
40
+
41
+ CHAT_EOS_TOKEN_ID = 32002
42
+
43
+ prompt = "How to get in a good university?"
44
+ formatted_prompt = (
45
+ f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
46
+ )
47
+
48
+
49
+ sequences = pipeline(
50
+ formatted_prompt,
51
+ do_sample=True,
52
+ top_k=50,
53
+ top_p = 0.9,
54
+ num_return_sequences=1,
55
+ repetition_penalty=1.1,
56
+ max_new_tokens=1024,
57
+ eos_token_id=CHAT_EOS_TOKEN_ID,
58
+ )
59
+
60
+ for seq in sequences:
61
+ print(f"Result: {seq['generated_text']}")
62
+ ```