Instructions to use AdrianME/SmolLM2-FT-MyDataset with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdrianME/SmolLM2-FT-MyDataset with Transformers:

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

pipe = pipeline("text-generation", model="AdrianME/SmolLM2-FT-MyDataset")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AdrianME/SmolLM2-FT-MyDataset")
model = AutoModelForCausalLM.from_pretrained("AdrianME/SmolLM2-FT-MyDataset")
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 AdrianME/SmolLM2-FT-MyDataset with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdrianME/SmolLM2-FT-MyDataset"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdrianME/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AdrianME/SmolLM2-FT-MyDataset

SGLang

How to use AdrianME/SmolLM2-FT-MyDataset 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 "AdrianME/SmolLM2-FT-MyDataset" \
    --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": "AdrianME/SmolLM2-FT-MyDataset",
		"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 "AdrianME/SmolLM2-FT-MyDataset" \
        --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": "AdrianME/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AdrianME/SmolLM2-FT-MyDataset with Docker Model Runner:
```
docker model run hf.co/AdrianME/SmolLM2-FT-MyDataset
```

AdrianME commited on Feb 25

Commit

4075d8c

verified ·

1 Parent(s): 2dd5ba6

End of training

Browse files

Files changed (4) hide show

README.md +2 -2
chat_template.jinja +1 -3
model.safetensors +1 -1
tokenizer_config.json +16 -1

README.md CHANGED Viewed

@@ -4,10 +4,10 @@ library_name: transformers
 model_name: SmolLM2-FT-MyDataset
 tags:
 - generated_from_trainer
-- trl
-- sft
 - module_1
 - smol-course
 licence: license
 ---

 model_name: SmolLM2-FT-MyDataset
 tags:
 - generated_from_trainer
 - module_1
 - smol-course
+- sft
+- trl
 licence: license
 ---

chat_template.jinja CHANGED Viewed

@@ -1,3 +1 @@
-{% for message in messages %}<|im_start|>{{ message['role'] }}
-{{ message['content'] }}<|im_end|>
-{% endfor %}


1	+ {% for message in messages %}{% if message['role'] == 'user' %}{{ '<\|im_start\|>user\n' + message['content'] + '<\|im_end\|>\n' }}{% elif message['role'] == 'system' %}{{ '<\|im_start\|>system\n' + message['content'] + '<\|im_end\|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<\|im_start\|>assistant\n' + message['content'] + '<\|im_end\|>\n' }}{% endif %}{% endfor %}

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b05221f9e9418ddb8c213103c1e1fdc886c214394c7a46afed27d06f8fa43d
 size 269060552

 version https://git-lfs.github.com/spec/v1
+oid sha256:44dc88f1896935cc72f871fcac45107cef2c4488a5b73eb71ce5dfa334d42531
 size 269060552

tokenizer_config.json CHANGED Viewed

@@ -5,8 +5,23 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": [
     "<|im_start|>",
-    "<|im_end|>"
   ],
   "is_local": false,
   "model_max_length": 8192,

   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": [
+    "<|endoftext|>",
     "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
   ],
   "is_local": false,
   "model_max_length": 8192,