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

Libraries

How to use unsloth/tinyllama with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/tinyllama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/tinyllama")
model = AutoModelForCausalLM.from_pretrained("unsloth/tinyllama")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/tinyllama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/unsloth/tinyllama

SGLang

How to use unsloth/tinyllama 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 "unsloth/tinyllama" \
    --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": "unsloth/tinyllama",
		"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 "unsloth/tinyllama" \
        --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": "unsloth/tinyllama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use unsloth/tinyllama with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/tinyllama to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/tinyllama to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/tinyllama to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/tinyllama",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/tinyllama with Docker Model Runner:
```
docker model run hf.co/unsloth/tinyllama
```

danielhanchen commited on Jan 2, 2024

Commit

b1e304c

1 Parent(s): 8281be5

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.model +3 -0
tokenizer_config.json +0 -3

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -28,7 +26,6 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,

 {
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
     }
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,