Spaces:
Runtime error
Runtime error
Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ license: mit
|
|
12 |
|
13 |
# Friendly Fincancial Bot
|
14 |
|
15 |
-
This is the Inference module of a 3-part FTI feature-training-inference **RAG-framework LLMOps** course. \
|
16 |
In this iteration, I've **replaced Falcon 7B Instruct** with the *currently-SoTa (Jan '24)* **Mistral-7B-Instruct-v0.2**, \
|
17 |
fine-tuned using **Unsloth** on financial questions and answers generated with the help of GPT-4, quantized \
|
18 |
and augmented with a 4bit QLoRa. \
|
@@ -23,7 +23,5 @@ most relevant news article to provide answers with real-time finance information
|
|
23 |
\
|
24 |
**#TODO:** Add citations to output to show end-user which article has been used to generate the output.
|
25 |
|
26 |
-
I have contributed to the original MIT licensed (ka-ching!) course which can be found here
|
27 |
-
|
28 |
-
## The LLMs kit: Build a production-ready real-time financial advisor system using streaming pipelines, RAG, and LLMOps
|
29 |
-
https://medium.com/decoding-ml/the-llms-kit-build-a-production-ready-real-time-financial-advisor-system-using-streaming-ffdcb2b50714
|
|
|
12 |
|
13 |
# Friendly Fincancial Bot
|
14 |
|
15 |
+
This is the Inference module of a 3-part **production-ready** FTI feature-training-inference **RAG-framework LLMOps** course. \
|
16 |
In this iteration, I've **replaced Falcon 7B Instruct** with the *currently-SoTa (Jan '24)* **Mistral-7B-Instruct-v0.2**, \
|
17 |
fine-tuned using **Unsloth** on financial questions and answers generated with the help of GPT-4, quantized \
|
18 |
and augmented with a 4bit QLoRa. \
|
|
|
23 |
\
|
24 |
**#TODO:** Add citations to output to show end-user which article has been used to generate the output.
|
25 |
|
26 |
+
I have contributed to the original MIT licensed (ka-ching!) course which can be found here:\
|
27 |
+
[https://medium.com/decoding-ml/the-llms-kit-build-a-production-ready-real-time-financial-advisor-system-using-streaming-ffdcb2b50714]
|
|
|
|