Instructions to use xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw with Transformers:

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

pipe = pipeline("text-generation", model="xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw")
model = AutoModelForCausalLM.from_pretrained("xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw", device_map="auto")
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 xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw

SGLang

How to use xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw 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 "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw" \
    --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": "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw",
		"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 "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw" \
        --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": "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw with Docker Model Runner:
```
docker model run hf.co/xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw
```

xv0y5ncu commited on Apr 6

Commit

d664076

verified ·

1 Parent(s): 467759c

Fix tokenizer_config: tokenizer_class=GPT2TokenizerFast

Browse files

Files changed (1) hide show

tokenizer_config.json +7 -0

tokenizer_config.json CHANGED Viewed

@@ -4,14 +4,21 @@
   "bos_token": "<|im_start|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>"
   ],
   "is_local": false,
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152
 }

   "bos_token": "<|im_start|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
+  "eot_token": "▁<EOT>",
   "errors": "replace",
   "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>"
   ],
+  "fill_token": "<FILL_ME>",
   "is_local": false,
+  "middle_token": "▁<MID>",
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
+  "prefix_token": "▁<PRE>",
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "GPT2TokenizerFast",
   "unk_token": "<|endoftext|>",
+  "use_default_system_prompt": false,
   "vocab_size": 49152
 }