Instructions to use fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym with Transformers:

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

pipe = pipeline("text-generation", model="fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym")
model = AutoModelForCausalLM.from_pretrained("fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Transformers.js

How to use fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym');

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym

SGLang

How to use fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym 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 "fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym" \
    --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": "fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym",
		"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 "fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym" \
        --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": "fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym
```

fbaldassarri commited on Feb 18, 2025

Commit

c9330d9

verified ·

1 Parent(s): f78ee05

Upload README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -14,8 +14,8 @@ tags:
 - safetensors
 - onnx
 - transformers.js
-model_name: SmolLM2 1.7B Instruct
-base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
 inference: false
 model_creator: HuggingFaceTB
 pipeline_tag: text-generation
@@ -26,7 +26,7 @@ quantized_by: fbaldassarri
 ## Model Information
-Quantized version of [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) using torch.float32 for quantization tuning.
 - 8 bits (INT8)
 - group size = 128
 - Symmetrical Quantization
@@ -36,7 +36,7 @@ Fast and low memory, 2-3X speedup (slight accuracy drop at W8G128)
 Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.5
-Note: this INT8 version of SmolLM2-1.7B-Instruct has been quantized to run inference through CPU.
 ## Replication Recipe
@@ -61,14 +61,14 @@ pip install -vvv --no-build-isolation -e .[cpu]
 ```
   from transformers import AutoModelForCausalLM, AutoTokenizer
-  model_name = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
   model = AutoModelForCausalLM.from_pretrained(model_name)
   tokenizer = AutoTokenizer.from_pretrained(model_name)
   from auto_round import AutoRound
   bits, group_size, sym, device, amp = 8, 128, True, 'cpu', False
   autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
   autoround.quantize()
-  output_dir = "./AutoRound/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_round-int8-gs128-sym"
   autoround.save_quantized(output_dir, format='auto_round', inplace=True)
 ```

 - safetensors
 - onnx
 - transformers.js
+model_name: SmolLM2 135M Instruct
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
 inference: false
 model_creator: HuggingFaceTB
 pipeline_tag: text-generation
 ## Model Information
+Quantized version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) using torch.float32 for quantization tuning.
 - 8 bits (INT8)
 - group size = 128
 - Symmetrical Quantization
 Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.5
+Note: this INT8 version of SmolLM2-135M-Instruct has been quantized to run inference through CPU.
 ## Replication Recipe
 ```
   from transformers import AutoModelForCausalLM, AutoTokenizer
+  model_name = "HuggingFaceTB/SmolLM2-135M-Instruct"
   model = AutoModelForCausalLM.from_pretrained(model_name)
   tokenizer = AutoTokenizer.from_pretrained(model_name)
   from auto_round import AutoRound
   bits, group_size, sym, device, amp = 8, 128, True, 'cpu', False
   autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
   autoround.quantize()
+  output_dir = "./AutoRound/HuggingFaceTB_SmolLM2-135M-Instruct-auto_round-int8-gs128-sym"
   autoround.save_quantized(output_dir, format='auto_round', inplace=True)
 ```