Update README.md
Browse files
README.md
CHANGED
|
@@ -43,34 +43,35 @@ This is a reinforcement learning model trained to predict real-time sales conver
|
|
| 43 |
- **Action Space**: Continuous (conversion probability 0-1)
|
| 44 |
- **Feature Extractor**: Custom Linear layers
|
| 45 |
|
| 46 |
-
## Quick Start
|
| 47 |
-
## Run On Colab With unsloth/gemma-3-4b-it-GGUF model and BAAI/bge-m3 opensource embeddings
|
| 48 |
|
| 49 |
-
[](https://colab.research.google.com/drive/19wcOQQs_wlEhHSQdOftOErjMjM8CjoaC?usp=sharing)
|
| 50 |
-
## Run Open-Source Model Directly
|
| 51 |
-
```bash
|
| 52 |
-
!git lfs install
|
| 53 |
-
!git clone https://huggingface.co/DeepMostInnovations/sales-conversion-model-reinf-learning
|
| 54 |
-
%cd sales-conversion-model-reinf-learning
|
| 55 |
-
|
| 56 |
-
!python opensource_inference.py --model_path sales_conversion_model
|
| 57 |
-
```
|
| 58 |
|
| 59 |
### Installation
|
| 60 |
-
Important to use python 3.
|
| 61 |
```bash
|
| 62 |
-
conda create -n
|
| 63 |
-
conda activate
|
| 64 |
pip install azure-openai stable-baselines3 numpy torch huggingface_hub
|
| 65 |
git lfs install
|
| 66 |
git clone https://huggingface.co/DeepMostInnovations/sales-conversion-model-reinf-learning
|
| 67 |
cd sales-conversion-model-reinf-learning
|
| 68 |
```
|
|
|
|
|
|
|
| 69 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
-
## Run
|
|
|
|
| 72 |
|
| 73 |
```bash
|
|
|
|
|
|
|
|
|
|
| 74 |
python sales_inference.py --model_path sales_model.zip --conversation_json sample_conv_generated.json --azure_api_key "api_key" --azure_endpoint "https://resource_name.openai.azure.com/" --azure_deployment_name "text-embedding-3-large" --azure_api_version "2023-12-01-preview" --embedding_dim 3072
|
| 75 |
```
|
| 76 |
## Output
|
|
|
|
| 43 |
- **Action Space**: Continuous (conversion probability 0-1)
|
| 44 |
- **Feature Extractor**: Custom Linear layers
|
| 45 |
|
|
|
|
|
|
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
### Installation
|
| 49 |
+
Important to use python 3.11 version for inference case, otherwise it will cause layer dim errors
|
| 50 |
```bash
|
| 51 |
+
conda create -n salespy11 pip python=3.11
|
| 52 |
+
conda activate salespy11
|
| 53 |
pip install azure-openai stable-baselines3 numpy torch huggingface_hub
|
| 54 |
git lfs install
|
| 55 |
git clone https://huggingface.co/DeepMostInnovations/sales-conversion-model-reinf-learning
|
| 56 |
cd sales-conversion-model-reinf-learning
|
| 57 |
```
|
| 58 |
+
## Quick Start
|
| 59 |
+
**Run On Colab With unsloth/gemma-3-4b-it-GGUF model and BAAI/bge-m3 opensource embeddings**
|
| 60 |
|
| 61 |
+
[](https://colab.research.google.com/drive/19wcOQQs_wlEhHSQdOftOErjMjM8CjoaC?usp=sharing)
|
| 62 |
+
|
| 63 |
+
## Run Open-Source Model Directly
|
| 64 |
+
```bash
|
| 65 |
+
!python opensource_inference.py --model_path sales_conversion_model
|
| 66 |
+
```
|
| 67 |
|
| 68 |
+
## Run azure embedding trained model
|
| 69 |
+
Important to use python 3.10 version for inference case, otherwise it will cause layer dim errors
|
| 70 |
|
| 71 |
```bash
|
| 72 |
+
conda create -n salespy10 pip python=3.110
|
| 73 |
+
conda activate salespy110
|
| 74 |
+
pip install azure-openai stable-baselines3 numpy torch huggingface_hub
|
| 75 |
python sales_inference.py --model_path sales_model.zip --conversation_json sample_conv_generated.json --azure_api_key "api_key" --azure_endpoint "https://resource_name.openai.azure.com/" --azure_deployment_name "text-embedding-3-large" --azure_api_version "2023-12-01-preview" --embedding_dim 3072
|
| 76 |
```
|
| 77 |
## Output
|