Instructions to use shareAI/Felguk0.5-turbo-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shareAI/Felguk0.5-turbo-preview with Transformers:

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

pipe = pipeline("text-generation", model="shareAI/Felguk0.5-turbo-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shareAI/Felguk0.5-turbo-preview", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shareAI/Felguk0.5-turbo-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shareAI/Felguk0.5-turbo-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shareAI/Felguk0.5-turbo-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shareAI/Felguk0.5-turbo-preview

SGLang

How to use shareAI/Felguk0.5-turbo-preview 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 "shareAI/Felguk0.5-turbo-preview" \
    --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": "shareAI/Felguk0.5-turbo-preview",
		"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 "shareAI/Felguk0.5-turbo-preview" \
        --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": "shareAI/Felguk0.5-turbo-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shareAI/Felguk0.5-turbo-preview with Docker Model Runner:
```
docker model run hf.co/shareAI/Felguk0.5-turbo-preview
```

The Felguk0.5-turbo-preview model is a preview version of a powerful language model developed by ShareAI. It is designed for text generation, conversational systems, and other NLP tasks. Built on the Transformer architecture, this model is optimized for high performance.

All Felguk Models on Hugging Face

Here’s a list of all available models under the felguk namespace on Hugging Face:

Model Name	Description	Link
`shareAI/Felguk0.5-turbo-preview`	A preview version of the Felguk model for text generation and conversation.	Model Page
`shareAI/Felguk0.5-base`	The base version of the Felguk model for general-purpose NLP tasks.	Model Page
`shareAI/Felguk0.5-large`	A larger version of the Felguk model with enhanced capabilities.	Model Page
`shareAI/Felguk0.5-multilingual`	A multilingual variant of the Felguk model for cross-language tasks.	Model Page

Note: Currently, only the Felguk0.5-turbo-preview model is available. The other models listed above are planned for future release and are not yet accessible.

Future Plans: We are excited to announce that Felguk v1 is in development! This next-generation model will feature improved performance, enhanced multilingual support, and new capabilities for advanced NLP tasks. Stay tuned for updates!

What Can It Do? 🚀

The Felguk0.5-turbo-preview model is a versatile tool for a wide range of NLP tasks. Here’s what it can do:

📝 Text Generation: Create high-quality text for stories, articles, or creative writing.
💬 Conversational AI: Power chatbots and virtual assistants with natural, human-like responses.
🌐 Multilingual Support: Handle multiple languages for global applications (coming soon in future versions).
🔍 Summarization: Generate concise summaries of long documents or articles.
❓ Question Answering: Provide accurate answers to user queries based on context.
🧠 Knowledge Integration: Leverage pre-trained knowledge for informed and context-aware responses.

Usage

To use the model with the transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "shareAI/Felguk0.5-turbo-preview"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example input
input_text = "Hello! How are you?"

# Tokenize and generate a response
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=50)

# Decode and print the result
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Downloads last month: -; Downloads are not tracked for this model. How to track