Instructions to use caelunshun/summarizer1-4b-fp8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caelunshun/summarizer1-4b-fp8-dynamic with Transformers:

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

pipe = pipeline("text-generation", model="caelunshun/summarizer1-4b-fp8-dynamic")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("caelunshun/summarizer1-4b-fp8-dynamic")
model = AutoModelForCausalLM.from_pretrained("caelunshun/summarizer1-4b-fp8-dynamic")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use caelunshun/summarizer1-4b-fp8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "caelunshun/summarizer1-4b-fp8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caelunshun/summarizer1-4b-fp8-dynamic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/caelunshun/summarizer1-4b-fp8-dynamic

SGLang

How to use caelunshun/summarizer1-4b-fp8-dynamic 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 "caelunshun/summarizer1-4b-fp8-dynamic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caelunshun/summarizer1-4b-fp8-dynamic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "caelunshun/summarizer1-4b-fp8-dynamic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caelunshun/summarizer1-4b-fp8-dynamic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use caelunshun/summarizer1-4b-fp8-dynamic with Docker Model Runner:
```
docker model run hf.co/caelunshun/summarizer1-4b-fp8-dynamic
```

summarizer1-4b-fp8-dynamic / config.json

caelunshun

Upload Qwen3ForCausalLM

3585160 verified 5 months ago

raw

history blame contribute delete

2.83 kB

	{
	"architectures": [
	"Qwen3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"eos_token_id": 151643,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": 9728,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"max_window_layers": 36,
	"model_type": "qwen3",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"pad_token_id": 151643,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "float-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": null,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "token",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": null,
	"num_bits": 8,
	"observer": "minmax",
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "channel",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	}
	},
	"format": "float-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.13.0"
	},
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000000,
	"sliding_window": null,
	"tie_word_embeddings": true,
	"transformers_version": "4.57.3",
	"use_cache": false,
	"use_sliding_window": false,
	"vocab_size": 151676
	}