Instructions to use martimfasantos/tinyllama-1.1b-sum-sft-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use martimfasantos/tinyllama-1.1b-sum-sft-full with Transformers:

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

pipe = pipeline("text-generation", model="martimfasantos/tinyllama-1.1b-sum-sft-full")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("martimfasantos/tinyllama-1.1b-sum-sft-full")
model = AutoModelForCausalLM.from_pretrained("martimfasantos/tinyllama-1.1b-sum-sft-full")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use martimfasantos/tinyllama-1.1b-sum-sft-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "martimfasantos/tinyllama-1.1b-sum-sft-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "martimfasantos/tinyllama-1.1b-sum-sft-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/martimfasantos/tinyllama-1.1b-sum-sft-full

SGLang

How to use martimfasantos/tinyllama-1.1b-sum-sft-full 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 "martimfasantos/tinyllama-1.1b-sum-sft-full" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "martimfasantos/tinyllama-1.1b-sum-sft-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "martimfasantos/tinyllama-1.1b-sum-sft-full" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "martimfasantos/tinyllama-1.1b-sum-sft-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use martimfasantos/tinyllama-1.1b-sum-sft-full with Docker Model Runner:
```
docker model run hf.co/martimfasantos/tinyllama-1.1b-sum-sft-full
```

tinyllama-1.1b-sum-sft-full

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the martimfasantos/openai-summarize-tldr dataset. It achieves the following results on the evaluation set:

Loss: 2.1350

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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.1307	0.9997	1476	2.1350

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1

Downloads last month: 7

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for martimfasantos/tinyllama-1.1b-sum-sft-full

Base model

TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

Finetuned

(105)

this model

Finetunes

4 models

martimfasantos
/

tinyllama-1.1b-sum-sft-full

tinyllama-1.1b-sum-sft-full

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for martimfasantos/tinyllama-1.1b-sum-sft-full

Dataset used to train martimfasantos/tinyllama-1.1b-sum-sft-full