Instructions to use KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("KayaTechAI/SLERP-IPT-Llama-3.1-8B-Financial-Instruct")
model = PeftModel.from_pretrained(base_model, "KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment")

Transformers

How to use KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment with Transformers:

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

pipe = pipeline("text-generation", model="KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment

SGLang

How to use KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment 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 "KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment" \
    --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": "KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment",
		"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 "KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment" \
        --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": "KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment with Docker Model Runner:
```
docker model run hf.co/KayaTechAI/SFT-Llama-3.1-8B-Financial-Instruct-Sentiment
```

SFT-Llama-3.1-8B-Financial-Instruct-Sentiment / tokenizer.json

KayaTechAI

Upload best LoRA checkpoint from FIN-Sentiment SFT (step 1470, eval_loss=0.179)

db8fa04 verified 26 days ago

Download

History Blame Contribute Delete

17.2 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 2e56cad9ac2a38f4b7de211953881b613c19e51838c05adf8f7984c139c2e8f5
Size of remote file:: 17.2 MB
SHA256:: 6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.