Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Customer Support Chatbot with LLaMA 3.1
|
| 2 |
|
| 3 |
> An end-to-end customer support chatbot solution powered by fine-tuned LLaMA 3.1 8B model, deployed using Flask, Docker, and AWS ECS.
|
|
@@ -59,18 +76,6 @@ The fine-tuned model is hosted on Hugging Face:
|
|
| 59 |
3. Set up AWS CodePipeline for CI/CD
|
| 60 |
4. Configure CloudWatch monitoring
|
| 61 |
|
| 62 |
-
---
|
| 63 |
-
base_model: unsloth/llama-3-8b-bnb-4bit
|
| 64 |
-
language:
|
| 65 |
-
- en
|
| 66 |
-
license: apache-2.0
|
| 67 |
-
tags:
|
| 68 |
-
- text-generation-inference
|
| 69 |
-
- transformers
|
| 70 |
-
- unsloth
|
| 71 |
-
- llama
|
| 72 |
-
- gguf
|
| 73 |
-
---
|
| 74 |
|
| 75 |
# Uploaded model
|
| 76 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- bitext/Bitext-customer-support-llm-chatbot-training-dataset
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- unsloth/llama-3-8b-bnb-4bit
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
tags:
|
| 11 |
+
- text-generation-inference
|
| 12 |
+
- transformers
|
| 13 |
+
- unsloth
|
| 14 |
+
- llama
|
| 15 |
+
- gguf
|
| 16 |
+
- Customer-Support-Bot
|
| 17 |
+
---
|
| 18 |
# Customer Support Chatbot with LLaMA 3.1
|
| 19 |
|
| 20 |
> An end-to-end customer support chatbot solution powered by fine-tuned LLaMA 3.1 8B model, deployed using Flask, Docker, and AWS ECS.
|
|
|
|
| 76 |
3. Set up AWS CodePipeline for CI/CD
|
| 77 |
4. Configure CloudWatch monitoring
|
| 78 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
# Uploaded model
|
| 81 |
|