Text Generation
PEFT
Safetensors
English
instruction-tuning
multi-task
reasoning
email
summarization
chat
lora
qwen
deepseek
conversational
Instructions to use GilbertAkham/deepseek-R1-multitask-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use GilbertAkham/deepseek-R1-multitask-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B") model = PeftModel.from_pretrained(base_model, "GilbertAkham/deepseek-R1-multitask-lora") - Notebooks
- Google Colab
- Kaggle
Update handler.py
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
import torch
|
| 3 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 4 |
|
| 5 |
-
MODEL_PATH = "
|
| 6 |
|
| 7 |
class EndpointHandler:
|
| 8 |
def __init__(self, path=""):
|
|
|
|
| 2 |
import torch
|
| 3 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 4 |
|
| 5 |
+
MODEL_PATH = "GilbertAkham/deepseek-R1-multitask-lora"
|
| 6 |
|
| 7 |
class EndpointHandler:
|
| 8 |
def __init__(self, path=""):
|