Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,54 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
quantized_by:
|
10 |
+
- kirp
|
11 |
+
pipeline_tag: text-generation
|
12 |
---
|
13 |
+
|
14 |
+
# TinyLlama-1.1B Chat v0.2 bin
|
15 |
+
- Model creator: [PY007](https://huggingface.co/PY007)
|
16 |
+
- Original model: [TinyLlama 1.1B Chat v0.2](https://huggingface.co/PY007/TinyLlama-1.1B-Chat-v0.2)
|
17 |
+
- Github: [TinyLlama](https://github.com/jzhang38/TinyLlama)
|
18 |
+
|
19 |
+
## Description
|
20 |
+
|
21 |
+
This repo contains llama2.c/llama2.mojo format model files for [PY007's TinyLlama 1.1B Chat v0.2](PY007/TinyLlama-1.1B-Chat-v0.2)
|
22 |
+
|
23 |
+
|
24 |
+
<!-- prompt-template start -->
|
25 |
+
|
26 |
+
## Prompt template: TinyLlama chat
|
27 |
+
|
28 |
+
```
|
29 |
+
<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n
|
30 |
+
```
|
31 |
+
|
32 |
+
Example:
|
33 |
+
|
34 |
+
```
|
35 |
+
<|im_start|>user
|
36 |
+
Explain huggingface.<|im_end|>
|
37 |
+
<|im_start|>assistant
|
38 |
+
Hugging Face is a platform for building and hosting open-source applications. It provides a simple interface for developers to build, deploy, and host any application on the web. Hugging Face offers a wide range of services, including:
|
39 |
+
|
40 |
+
1. API Gateway: This service allows developers to create REST APIs that can be accessed by other Hugging Face services.
|
41 |
+
|
42 |
+
2. Functions: This service provides functions that can be used for processing data and making predictions.
|
43 |
+
|
44 |
+
3. Transformers: These are a set of algorithms that allow developers to process large amounts of text data and generate new content.
|
45 |
+
|
46 |
+
4. Datasets: Hugging Face provides datasets that can be used to train models, evaluate them, and make predictions.
|
47 |
+
|
48 |
+
5. CLI: This service provides a command-line interface for developers to build, deploy, and manage their applications.
|
49 |
+
|
50 |
+
6. Documentation: This service provides documentation for the different services and features available on Hugging Face's platform.
|
51 |
+
|
52 |
+
7. Community: The Hugging Face community is made up of developers, data scientists, and other experts who can provide support and resources for using and building on Hugging Face's platforms.<|im_end|>
|
53 |
+
```
|
54 |
+
<!-- prompt-template end -->
|