Instructions to use SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2 with Transformers:

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

pipe = pipeline("text-generation", model="SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2")
model = AutoModelForCausalLM.from_pretrained("SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2

SGLang

How to use SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2 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 "SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2" \
    --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": "SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2",
		"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 "SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2" \
        --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": "SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2 with Docker Model Runner:
```
docker model run hf.co/SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2
```

tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora-v2

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5376
Rewards/chosen: 0.2709
Rewards/rejected: -0.4042
Rewards/accuracies: 0.7230
Rewards/margins: 0.6751
Logps/rejected: -319.7874
Logps/chosen: -399.9467
Logits/rejected: -4.0164
Logits/chosen: -4.1297

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 32
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.5681	1.0	968	0.5376	0.2709	-0.4042	0.7230	0.6751	-319.7874	-399.9467	-4.0164	-4.1297

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.14.6
Tokenizers 0.14.1

Downloads last month: 3