CreitinGameplays
commited on
Commit
•
bf43f6a
1
Parent(s):
103312a
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,39 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
datasets:
|
4 |
+
- Xilabs/instructmix
|
5 |
+
- CreitinGameplays/small-chat-assistant-for-bloom
|
6 |
+
- sahil2801/CodeAlpaca-20k
|
7 |
+
language:
|
8 |
+
- en
|
9 |
---
|
10 |
+
## BLOOM 3b Fine-tuned for Chat Assistant
|
11 |
+
|
12 |
+
**Model Name:** BLOOM 3b
|
13 |
+
|
14 |
+
**Model Architecture:** bloom
|
15 |
+
|
16 |
+
**Short Description:** This model is a fine-tuned version of the BLOOM 3b large language model, focusing on conversational interactions between a user and an AI assistant. The fine-tuning process leveraged two datasets: "vicgalle/alpaca-gpt4" and "CreitinGameplays/small-chat-assistant-for-bloom". These datasets provided examples of question-and-answer exchanges and dialogues between users and AI assistants.
|
17 |
+
|
18 |
+
**Intended Use:** This model is intended for research purposes and exploration of conversational AI applications. It can be used for tasks like:
|
19 |
+
|
20 |
+
* Generating responses to user prompts in a chat assistant setting.
|
21 |
+
* Creating examples of chatbot interactions for further development.
|
22 |
+
* Studying the capabilities of large language models for conversation.
|
23 |
+
|
24 |
+
**Limitations:**
|
25 |
+
|
26 |
+
* **Fine-tuning Focus:** The model's performance is optimized for the specific format and context of the fine-tuning data. It may not generalize well to significantly different conversation styles or topics.
|
27 |
+
* **Potential Biases:** The model may inherit biases from the training data. It's important to be aware of these potential biases and use the model responsibly.
|
28 |
+
* **Limited Factual Accuracy:** Large language models are still under development and may generate responses that are not entirely factually accurate. It's important to verify information generated by the model with other sources.
|
29 |
+
|
30 |
+
**Specific Input Format:**
|
31 |
+
|
32 |
+
The model was fine-tuned using a specific input format that separates the system prompt, user prompt, and assistant response with special tokens:
|
33 |
+
|
34 |
+
```
|
35 |
+
<|system|> {system prompt} </s> <|prompter|> {user prompt} </s> <|assistant|> </s> {model prediction} ```
|
36 |
+
|
37 |
+
Using this format when interacting with the model can improve its performance and generate more relevant responses.
|
38 |
+
|
39 |
+
**Disclaimer:** This model is for research and exploration purposes only. It should not be used in any applications that require high levels of accuracy or reliability.
|