|
|
--- |
|
|
base_model: Qwen/Qwen3-4B-Instruct-2507 |
|
|
tags: |
|
|
- salesforce |
|
|
- customer-service |
|
|
- crm |
|
|
- lora |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- urm3l/SalesforceTraining |
|
|
--- |
|
|
|
|
|
# Qwen3 4B Salesforce Fine-tuned |
|
|
|
|
|
This model is a fine-tuned version of Qwen3-4B-Instruct on Salesforce Q&A data. |
|
|
|
|
|
## Usage |
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
from peft import PeftModel |
|
|
|
|
|
base_model = "Qwen/Qwen3-4B-Instruct-2507" |
|
|
adapter_model = "YOUR_USERNAME/qwen3-4b-salesforce-finetuned" |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(base_model) |
|
|
model = PeftModel.from_pretrained(model, adapter_model) |
|
|
tokenizer = AutoTokenizer.from_pretrained(adapter_model) |
