Instructions to use nairanu6115/tinyllama-erp-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nairanu6115/tinyllama-erp-merged with Transformers:

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

pipe = pipeline("text-generation", model="nairanu6115/tinyllama-erp-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nairanu6115/tinyllama-erp-merged")
model = AutoModelForCausalLM.from_pretrained("nairanu6115/tinyllama-erp-merged")
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 nairanu6115/tinyllama-erp-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nairanu6115/tinyllama-erp-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nairanu6115/tinyllama-erp-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nairanu6115/tinyllama-erp-merged

SGLang

How to use nairanu6115/tinyllama-erp-merged 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 "nairanu6115/tinyllama-erp-merged" \
    --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": "nairanu6115/tinyllama-erp-merged",
		"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 "nairanu6115/tinyllama-erp-merged" \
        --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": "nairanu6115/tinyllama-erp-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nairanu6115/tinyllama-erp-merged with Docker Model Runner:
```
docker model run hf.co/nairanu6115/tinyllama-erp-merged
```

tinyllama-erp-merged

This model is a fine-tuned and merged version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 for ERP-related question answering and text generation.

Model details

Base model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Model type: Causal language model
Framework: Hugging Face Transformers
Format: Safetensors
Use case: ERP question answering and assistance

Intended use

This model is intended for:

ERP-related question answering
General business process assistance

Limitations

It may produce incomplete or incorrect answers.
It should not be used for critical financial or legal decisions without human review.
Output quality depends on the training data.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

repo_id = "nairanu6115/tinyllama-erp-merged"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = "What is a purchase order?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=200,
        do_sample=False,
        pad_token_id=tokenizer.eos_token_id
    )

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 4

Safetensors

Model size

1B params

Tensor type

F16

Model tree for nairanu6115/tinyllama-erp-merged

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Finetuned

(555)

this model