Instructions to use DILAB-HYU/DialRet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DILAB-HYU/DialRet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DILAB-HYU/DialRet")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DILAB-HYU/DialRet") model = AutoModelForCausalLM.from_pretrained("DILAB-HYU/DialRet") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use DILAB-HYU/DialRet with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DILAB-HYU/DialRet" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DILAB-HYU/DialRet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DILAB-HYU/DialRet
- SGLang
How to use DILAB-HYU/DialRet with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "DILAB-HYU/DialRet" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DILAB-HYU/DialRet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "DILAB-HYU/DialRet" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DILAB-HYU/DialRet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DILAB-HYU/DialRet with Docker Model Runner:
docker model run hf.co/DILAB-HYU/DialRet
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ library_name: transformers
|
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
license: mit
|
| 7 |
base_model:
|
| 8 |
-
-
|
| 9 |
---
|
| 10 |
|
| 11 |
|
|
@@ -36,7 +36,7 @@ Yohan Na*, Dahye Kim*, and Dong-Kyu chae.
|
|
| 36 |
<br>
|
| 37 |
|
| 38 |
## Introduction
|
| 39 |
-
DialRet is a dialogue-specific language model designed for multi-session conversations.
|
| 40 |
Instead of using memory modules, it leverages long-context LMs and instruction-tuning across eight tasks (e.g., dialogue generation, summarization, speaker relation extraction).
|
| 41 |
It improves understanding and retention of past dialogues.
|
| 42 |
|
|
|
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
license: mit
|
| 7 |
base_model:
|
| 8 |
+
- pinkmanlove/llama-7b-hf
|
| 9 |
---
|
| 10 |
|
| 11 |
|
|
|
|
| 36 |
<br>
|
| 37 |
|
| 38 |
## Introduction
|
| 39 |
+
DialRet is a dialogue-specific language model designed for multi-session conversations. (base model: llama-1-7b)
|
| 40 |
Instead of using memory modules, it leverages long-context LMs and instruction-tuning across eight tasks (e.g., dialogue generation, summarization, speaker relation extraction).
|
| 41 |
It improves understanding and retention of past dialogues.
|
| 42 |
|