Instructions to use Builder123/tinyllama-revops-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Builder123/tinyllama-revops-finetuned with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
model = PeftModel.from_pretrained(base_model, "Builder123/tinyllama-revops-finetuned")

Transformers

How to use Builder123/tinyllama-revops-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="Builder123/tinyllama-revops-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Builder123/tinyllama-revops-finetuned", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Builder123/tinyllama-revops-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Builder123/tinyllama-revops-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Builder123/tinyllama-revops-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Builder123/tinyllama-revops-finetuned

SGLang

How to use Builder123/tinyllama-revops-finetuned 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 "Builder123/tinyllama-revops-finetuned" \
    --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": "Builder123/tinyllama-revops-finetuned",
		"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 "Builder123/tinyllama-revops-finetuned" \
        --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": "Builder123/tinyllama-revops-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Builder123/tinyllama-revops-finetuned with Docker Model Runner:
```
docker model run hf.co/Builder123/tinyllama-revops-finetuned
```

RevOpsLM

A language model trained on Salesforce Agentforce, NetSuite AI, and SaaS Revenue Recognition (ASC 606) concepts using a LoRA fine-tuned adapter for TinyLlama-1.1B-Chat.

Model Description

This is a proof-of-concept project demonstrating LoRA fine-tuning techniques applied to a language model. The adapter was trained on 50 curated examples covering:

Salesforce Agentforce (20 examples): Agent types, RAG, topics, guardrails, triggers, and analytics
NetSuite AI Features (15 examples): Text Enhancer, Analytics Warehouse, Smart Alerts, and automation capabilities
SaaS Revenue Recognition (15 examples): ASC 606 compliance, performance obligations, deferred revenue, and contract accounting

Important: This is a learning exercise with limited training data. The model demonstrates fine-tuning methodology and is not meant for production use.

Resources

📂 GitHub Repository
📓 Training Notebook

Training Details

Base Model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Fine-Tuning Method: LoRA (Low-Rank Adaptation)
Training Examples: 50
Epochs: 3
Hardware: Google Colab T4 GPU
Training Time: ~8 minutes
LoRA Parameters: r=8, alpha=16, dropout=0.05

How to Use

To use this model, you'll need to load both the base model and this LoRA adapter:

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
adapter_model = "Builder123/tinyllama-revops-finetuned"

tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto")
model = PeftModel.from_pretrained(model, adapter_model)

# Generate response
prompt = "User: What is ASC 606?\nAssistant:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Limitations

Trained on limited data - responses may be inaccurate or incomplete
Not suitable for production use without additional training
May hallucinate or provide outdated information
Should be verified against official documentation

Intended Use

This model is intended for:

Educational purposes and learning about fine-tuning techniques
Demonstrating LoRA methodology
Portfolio/project showcase

License

This model follows the license of the base TinyLlama model (Apache 2.0).

Author

Created by Vladimir Parfenov.

Downloads last month: 14

Model tree for Builder123/tinyllama-revops-finetuned

Base model

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

Adapter

(1498)

this model