Instructions to use BarudakLearning/terTATa-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BarudakLearning/terTATa-LLM with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-2-Mistral-7B-DPO")
model = PeftModel.from_pretrained(base_model, "BarudakLearning/terTATa-LLM")

Transformers

How to use BarudakLearning/terTATa-LLM with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BarudakLearning/terTATa-LLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BarudakLearning/terTATa-LLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BarudakLearning/terTATa-LLM

SGLang

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

Docker Model Runner
How to use BarudakLearning/terTATa-LLM with Docker Model Runner:
```
docker model run hf.co/BarudakLearning/terTATa-LLM
```

terTATa-LLM

File size: 784 Bytes

28210ef

{
  "model_name": "tat-llm-final-e4",
  "base_model": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
  "tokenizer": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
  "adapter_type": "LoRA",
  "adapter_config": {
    "r": 64,
    "alpha": 16,
    "dropout": 0.1,
    "bias": "none"
  },
  "training": {
    "dataset": "TAT-QA (train.json)",
    "num_examples": 9000,
    "num_epochs": 4,
    "max_seq_length": 1024,
    "batch_size_per_device": 2,
    "learning_rate": 0.0002,
    "lr_scheduler": "constant",
    "fp16": false,
    "bf16": true,
    "optimizer": "AdamW (via Trainer)"
  },
  "notes": "Instruction-tuned with simplified prompt format. No evaluation run due to memory constraints. Use .generate() for inference.",
  "created_by": "Your Name or Team",
  "date": "2025-07-08"
}