Instructions to use AssistantsLab/SmolLM2-360M-humanized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AssistantsLab/SmolLM2-360M-humanized with Transformers:

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

pipe = pipeline("text-generation", model="AssistantsLab/SmolLM2-360M-humanized")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AssistantsLab/SmolLM2-360M-humanized")
model = AutoModelForCausalLM.from_pretrained("AssistantsLab/SmolLM2-360M-humanized")
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 AssistantsLab/SmolLM2-360M-humanized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AssistantsLab/SmolLM2-360M-humanized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AssistantsLab/SmolLM2-360M-humanized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AssistantsLab/SmolLM2-360M-humanized

SGLang

How to use AssistantsLab/SmolLM2-360M-humanized 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 "AssistantsLab/SmolLM2-360M-humanized" \
    --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": "AssistantsLab/SmolLM2-360M-humanized",
		"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 "AssistantsLab/SmolLM2-360M-humanized" \
        --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": "AssistantsLab/SmolLM2-360M-humanized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AssistantsLab/SmolLM2-360M-humanized with Docker Model Runner:
```
docker model run hf.co/AssistantsLab/SmolLM2-360M-humanized
```

Michielo commited on Feb 10, 2025

Commit

88853a6

verified ·

1 Parent(s): 2c2fe6e

Upload 9 files

Browse files

Files changed (5) hide show

config.json +8 -8
generation_config.json +1 -1
model.safetensors +2 -2
tokenizer.json +2 -14
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,16 +9,16 @@
   "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 576,
-  "initializer_range": 0.041666666666666664,
-  "intermediate_size": 1536,
   "is_llama_config": true,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
@@ -33,7 +33,7 @@
       "q4f16": "float16"
     }
   },
-  "transformers_version": "4.48.1",
   "use_cache": true,
   "vocab_size": 49152
 }

 {
+  "_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
   "is_llama_config": true,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
       "q4f16": "float16"
     }
   },
+  "transformers_version": "4.48.3",
   "use_cache": true,
   "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": "4.48.1"
 }

   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
+  "transformers_version": "4.48.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e4d809f3312d7981b7ee508e28d26e5ad8d892052276450c453aca8e9e33c9
-size 269060552

 version https://git-lfs.github.com/spec/v1
+oid sha256:6867677f24aa92ca496a27336e1936dcc2e334354806a69bfee7d3c960748d0f
+size 723674912

tokenizer.json CHANGED Viewed

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 8192,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Left",
-    "pad_to_multiple_of": null,
-    "pad_id": 2,
-    "pad_type_id": 0,
-    "pad_token": "<|im_end|>"
-  },
   "added_tokens": [
     {
       "id": 0,

 {
   "version": "1.0",
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b68a9f1738998eff41b91018764ad78d201106833f65c8eebdc38dd2bac9b45
 size 6200

 version https://git-lfs.github.com/spec/v1
+oid sha256:8288702bf1db05beb5371c5042435c0caec211ef529e54f10857324941950ccf
 size 6200