Instructions to use osidenna/SoftwareRequirements-T5-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use osidenna/SoftwareRequirements-T5-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="osidenna/SoftwareRequirements-T5-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("osidenna/SoftwareRequirements-T5-Base")
model = AutoModelForSeq2SeqLM.from_pretrained("osidenna/SoftwareRequirements-T5-Base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use osidenna/SoftwareRequirements-T5-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "osidenna/SoftwareRequirements-T5-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osidenna/SoftwareRequirements-T5-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/osidenna/SoftwareRequirements-T5-Base

SGLang

How to use osidenna/SoftwareRequirements-T5-Base 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 "osidenna/SoftwareRequirements-T5-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osidenna/SoftwareRequirements-T5-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "osidenna/SoftwareRequirements-T5-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osidenna/SoftwareRequirements-T5-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use osidenna/SoftwareRequirements-T5-Base with Docker Model Runner:
```
docker model run hf.co/osidenna/SoftwareRequirements-T5-Base
```

Oumoukelthoum sidenna commited on Aug 2, 2023

Commit

fbf9ebc

1 Parent(s): c08dae7

Update README.md

Browse files

![t5-large-chatting.png](https://cdn-uploads.huggingface.co/production/uploads/64b62e55d57e02621dc6ef20/bIyYlQmO97eLmXqJYF_UH.png)

Files changed (1) hide show

README.md +21 -4

README.md CHANGED Viewed

@@ -1,4 +1,21 @@
----
-license: apache-2.0
-pipeline_tag: conversational
----

+# Model Card for Fine-tuned T5-Base Conversational Model
+## Model Details
+- **Model name:** Fine-tuned T5-base Conversational Model
+- **Model type:** Transformer-based language model
+- **Original model:** T5-base from Hugging Face model hub
+- **Fine-tuning details:** The model has been fine-tuned on a custom conversational dataset. It includes a variety of dialogues covering multiple topics, aimed at increasing the model's ability to respond accurately and engagingly in conversational tasks.
+## Intended Use
+This model is intended for use in conversation-based applications. These can range from chatbots to virtual assistants, customer support automation, and more.
+## Examples
+![Example Conversation](https://cdn-uploads.huggingface.co/production/uploads/64b62e55d57e02621dc6ef20/bIyYlQmO97eLmXqJYF_UH.png)
+The above image showcases a sample conversation that took place between the user and the chatbot powered by our fine-tuned T5-base model. As seen, the model is able to generate engaging and contextually appropriate responses.