Instructions to use ereniko/SmolLLM2-135M-Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ereniko/SmolLLM2-135M-Code with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-135M-Instruct")
model = PeftModel.from_pretrained(base_model, "ereniko/SmolLLM2-135M-Code")

Transformers

How to use ereniko/SmolLLM2-135M-Code with Transformers:

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

pipe = pipeline("text-generation", model="ereniko/SmolLLM2-135M-Code")
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("ereniko/SmolLLM2-135M-Code", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ereniko/SmolLLM2-135M-Code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ereniko/SmolLLM2-135M-Code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ereniko/SmolLLM2-135M-Code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ereniko/SmolLLM2-135M-Code

SGLang

How to use ereniko/SmolLLM2-135M-Code 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 "ereniko/SmolLLM2-135M-Code" \
    --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": "ereniko/SmolLLM2-135M-Code",
		"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 "ereniko/SmolLLM2-135M-Code" \
        --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": "ereniko/SmolLLM2-135M-Code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ereniko/SmolLLM2-135M-Code with Docker Model Runner:
```
docker model run hf.co/ereniko/SmolLLM2-135M-Code
```

ereniko commited on Jul 4

Commit

10fdb73

verified ·

1 Parent(s): 50ce734

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -4

README.md CHANGED Viewed

@@ -18,6 +18,8 @@ license: cc-by-nc-4.0
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ```python
@@ -38,10 +40,6 @@ ask("Write a Python function to reverse a string")
 ## Training procedure
 This model was trained with SFT.
 ### Framework versions

 This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
+It's not anything magic, I just made this to test an Nvidia A30. It's hard to find on the  cloud, but it's a really nice budget GPU for training with its low price and HBM.
 ## Quick start
 ```python
 ## Training procedure
 This model was trained with SFT.
 ### Framework versions