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

Libraries

How to use MUTSC/SmolLM2-FT-DPO with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MUTSC/SmolLM2-FT-DPO")
model = AutoModelForCausalLM.from_pretrained("MUTSC/SmolLM2-FT-DPO")
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 Settings

vLLM

How to use MUTSC/SmolLM2-FT-DPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MUTSC/SmolLM2-FT-DPO

SGLang

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

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

MUTSC commited on Apr 15, 2025

Commit

a87990a

verified ·

1 Parent(s): 1164ed9

End of training

Browse files

Files changed (6) hide show

README.md +6 -6
config.json +1 -2
generation_config.json +1 -1
model.safetensors +1 -1
runs/Apr15_11-15-36_794992d02057/events.out.tfevents.1744716197.794992d02057.316.0 +3 -0
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -29,18 +29,18 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/tdva-etsit-etsit-universidad-politecnica-de-madrid/huggingface/runs/xt8b8r98)
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 ### Framework versions
-- TRL: 0.13.0
-- Transformers: 4.47.1
-- Pytorch: 2.5.1+cu121
-- Datasets: 3.2.0
-- Tokenizers: 0.21.0
 ## Citations

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/tdva-etsit-etsit-universidad-politecnica-de-madrid/huggingface/runs/xx90d4xp)
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 ### Framework versions
+- TRL: 0.16.1
+- Transformers: 4.51.1
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
 ## Citations

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Bipul8765/SmolLM2-FT-MyDataset",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,7 +26,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
   "use_cache": false,
   "vocab_size": 49152
 }

 {
   "architectures": [
     "LlamaForCausalLM"
   ],
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
   "use_cache": false,
   "vocab_size": 49152
 }

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.47.1"
 }

   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
+  "transformers_version": "4.51.1"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51623cec056e3dea0591898efc26bb1fe93f0bf3df111787fdcbefdcdfd899a
 size 538090408

 version https://git-lfs.github.com/spec/v1
+oid sha256:22c240c86f5f39b017382fe34df765b359abf2717448ef52dd48225c78c80d27
 size 538090408

runs/Apr15_11-15-36_794992d02057/events.out.tfevents.1744716197.794992d02057.316.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0200023bf5579e5e52b9526272db5806049e2320a41f16a2394c617c7d653c
+size 142459

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e730b53db66e1b42ff915b2163758b8548e5ef33922820a04f9f3bc9f40d59
-size 6264

 version https://git-lfs.github.com/spec/v1
+oid sha256:7b0d07b9d78b9da84ff7c173486953a7ac569e2f222eaa04754d3821addbdf33
+size 6200