Instructions to use Jayant9928/tnayaj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jayant9928/tnayaj with Transformers:

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

pipe = pipeline("text-generation", model="Jayant9928/tnayaj")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jayant9928/tnayaj")
model = AutoModelForCausalLM.from_pretrained("Jayant9928/tnayaj")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Jayant9928/tnayaj with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jayant9928/tnayaj"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jayant9928/tnayaj",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jayant9928/tnayaj

SGLang

How to use Jayant9928/tnayaj 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 "Jayant9928/tnayaj" \
    --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": "Jayant9928/tnayaj",
		"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 "Jayant9928/tnayaj" \
        --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": "Jayant9928/tnayaj",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jayant9928/tnayaj with Docker Model Runner:
```
docker model run hf.co/Jayant9928/tnayaj
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

The tnayaj-8B model is an innovative open-source language model specifically engineered for the biomedical domain. Crafted by Jayant AI Labs, this model harnesses state-of-the-art methodologies to achieve unparalleled performance across various biomedical tasks.

🏥 Specialization in medicine: tnayaj-8B caters to the intricate linguistic and informational demands of the medical and life sciences realms. Its refinement stems from extensive training on a comprehensive biomedical dataset, enabling precise and articulate text generation within the domain.

🎓 Exceptional Performance: Boasting a staggering 8 billion parameters 🧠 Advanced Training Methodologies: tnayaj-8B builds upon the foundational prowess of the Meta-Llama-3-8B-Instruct .It integrates the DPO dataset and a tailored array of medical instruction data for refinement. Central to its training regimen are meticulously curated components, including:

Downloads last month: 8

Safetensors

Model size

8B params

Tensor type

F16

Model tree for Jayant9928/tnayaj

Quantizations

1 model

Jayant9928
/

tnayaj

Model tree for Jayant9928/tnayaj

Spaces using Jayant9928/tnayaj 9