Text Generation
Transformers
Safetensors
GGUF
English
llama
conversational
text-generation-inference
Inference Endpoints
PY007 commited on
Commit
1c3ffd2
โ€ข
1 Parent(s): ab3b267

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -0
README.md CHANGED
@@ -1,3 +1,58 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ๐Ÿš€๐Ÿš€. 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-955k-2T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T). We follow the [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/edit/main/README.md)'s training recipe. The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
24
+ We then further aligned the model with [๐Ÿค— TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4."
25
+
26
+
27
+ #### How to use
28
+ You will need the transformers>=4.34
29
+ Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
30
+
31
+ ```python
32
+ # Install transformers from source - only needed for versions <= v4.34
33
+ # pip install git+https://github.com/huggingface/transformers.git
34
+ # pip install accelerate
35
+
36
+ import torch
37
+ from transformers import pipeline
38
+
39
+ pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v0.6", torch_dtype=torch.bfloat16, device_map="auto")
40
+
41
+ # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
42
+ messages = [
43
+ {
44
+ "role": "system",
45
+ "content": "You are a friendly chatbot who always responds in the style of a pirate",
46
+ },
47
+ {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
48
+ ]
49
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
50
+ outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
51
+ print(outputs[0]["generated_text"])
52
+ # <|system|>
53
+ # You are a friendly chatbot who always responds in the style of a pirate.</s>
54
+ # <|user|>
55
+ # How many helicopters can a human eat in one sitting?</s>
56
+ # <|assistant|>
57
+ # ...
58
+ ```