Instructions to use dvijay/tiny-llama-oa-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dvijay/tiny-llama-oa-qlora with Transformers:

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

pipe = pipeline("text-generation", model="dvijay/tiny-llama-oa-qlora")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dvijay/tiny-llama-oa-qlora")
model = AutoModelForCausalLM.from_pretrained("dvijay/tiny-llama-oa-qlora")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dvijay/tiny-llama-oa-qlora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dvijay/tiny-llama-oa-qlora

SGLang

How to use dvijay/tiny-llama-oa-qlora 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 "dvijay/tiny-llama-oa-qlora" \
    --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": "dvijay/tiny-llama-oa-qlora",
		"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 "dvijay/tiny-llama-oa-qlora" \
        --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": "dvijay/tiny-llama-oa-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dvijay/tiny-llama-oa-qlora with Docker Model Runner:
```
docker model run hf.co/dvijay/tiny-llama-oa-qlora
```

dvijay/tiny-llama-oa-qlora

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

Loss: 1.4810

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.5565	1.02	105	1.5177
1.5181	2.03	211	1.4840
1.3823	2.93	306	1.4810

Framework versions

Transformers 4.35.2
Pytorch 2.0.1+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 4

Model tree for dvijay/tiny-llama-oa-qlora

Base model

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

Quantized

(13)

this model