Instructions to use Jaidchen/Focus-Red-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jaidchen/Focus-Red-Int4 with Transformers:

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

pipe = pipeline("text-generation", model="Jaidchen/Focus-Red-Int4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jaidchen/Focus-Red-Int4")
model = AutoModelForCausalLM.from_pretrained("Jaidchen/Focus-Red-Int4", 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 Jaidchen/Focus-Red-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jaidchen/Focus-Red-Int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jaidchen/Focus-Red-Int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jaidchen/Focus-Red-Int4

SGLang

How to use Jaidchen/Focus-Red-Int4 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 "Jaidchen/Focus-Red-Int4" \
    --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": "Jaidchen/Focus-Red-Int4",
		"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 "Jaidchen/Focus-Red-Int4" \
        --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": "Jaidchen/Focus-Red-Int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jaidchen/Focus-Red-Int4 with Docker Model Runner:
```
docker model run hf.co/Jaidchen/Focus-Red-Int4
```

Focus-Red-Int4

File size: 6,585 Bytes

186d814

{"attention_bias":false,"attention_dropout":0,"attn_output_gate":true,"bos_token_id":248044,"dtype":"bfloat16","eos_token_id":248044,"full_attention_interval":4,"head_dim":256,"hidden_act":"silu","hidden_size":5120,"initializer_range":0.02,"intermediate_size":17408,"layer_types":["linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention","linear_attention","linear_attention","linear_attention","full_attention"],"linear_conv_kernel_dim":4,"linear_key_head_dim":128,"linear_num_key_heads":16,"linear_num_value_heads":48,"linear_value_head_dim":128,"mamba_ssm_dtype":"float32","max_position_embeddings":262144,"model_type":"qwen3_5_text","num_attention_heads":24,"num_hidden_layers":64,"num_key_value_heads":4,"output_gate_type":"swish","pad_token_id":null,"partial_rotary_factor":0.25,"rms_norm_eps":0.000001,"rope_parameters":{"mrope_interleaved":true,"mrope_section":[11,11,10],"partial_rotary_factor":0.25,"rope_theta":10000000,"rope_type":"default"},"tie_word_embeddings":false,"use_cache":true,"vocab_size":248320,"architectures":["Qwen3_5ForCausalLM"],"transformers_version":"5.8.0.dev0","quantization_config":{"config_groups":{"group_0":{"format":"pack-quantized","input_activations":null,"output_activations":null,"targets":["Linear"],"weights":{"actorder":null,"block_structure":null,"dynamic":false,"group_size":32,"num_bits":4,"observer":"mse","observer_kwargs":{},"scale_dtype":null,"strategy":"group","symmetric":false,"type":"int","zp_dtype":"torch.int8"}}},"format":"pack-quantized","global_compression_ratio":null,"ignore":["model.layers.0.linear_attn.in_proj_a","model.layers.0.linear_attn.in_proj_b","model.layers.1.linear_attn.in_proj_a","model.layers.1.linear_attn.in_proj_b","model.layers.10.linear_attn.in_proj_a","model.layers.10.linear_attn.in_proj_b","model.layers.12.linear_attn.in_proj_a","model.layers.12.linear_attn.in_proj_b","model.layers.13.linear_attn.in_proj_a","model.layers.13.linear_attn.in_proj_b","model.layers.14.linear_attn.in_proj_a","model.layers.14.linear_attn.in_proj_b","model.layers.16.linear_attn.in_proj_a","model.layers.16.linear_attn.in_proj_b","model.layers.17.linear_attn.in_proj_a","model.layers.17.linear_attn.in_proj_b","model.layers.18.linear_attn.in_proj_a","model.layers.18.linear_attn.in_proj_b","model.layers.2.linear_attn.in_proj_a","model.layers.2.linear_attn.in_proj_b","model.layers.20.linear_attn.in_proj_a","model.layers.20.linear_attn.in_proj_b","model.layers.21.linear_attn.in_proj_a","model.layers.21.linear_attn.in_proj_b","model.layers.22.linear_attn.in_proj_a","model.layers.22.linear_attn.in_proj_b","model.layers.24.linear_attn.in_proj_a","model.layers.24.linear_attn.in_proj_b","model.layers.25.linear_attn.in_proj_a","model.layers.25.linear_attn.in_proj_b","model.layers.26.linear_attn.in_proj_a","model.layers.26.linear_attn.in_proj_b","model.layers.28.linear_attn.in_proj_a","model.layers.28.linear_attn.in_proj_b","model.layers.29.linear_attn.in_proj_a","model.layers.29.linear_attn.in_proj_b","model.layers.30.linear_attn.in_proj_a","model.layers.30.linear_attn.in_proj_b","model.layers.32.linear_attn.in_proj_a","model.layers.32.linear_attn.in_proj_b","model.layers.33.linear_attn.in_proj_a","model.layers.33.linear_attn.in_proj_b","model.layers.34.linear_attn.in_proj_a","model.layers.34.linear_attn.in_proj_b","model.layers.36.linear_attn.in_proj_a","model.layers.36.linear_attn.in_proj_b","model.layers.37.linear_attn.in_proj_a","model.layers.37.linear_attn.in_proj_b","model.layers.38.linear_attn.in_proj_a","model.layers.38.linear_attn.in_proj_b","model.layers.4.linear_attn.in_proj_a","model.layers.4.linear_attn.in_proj_b","model.layers.40.linear_attn.in_proj_a","model.layers.40.linear_attn.in_proj_b","model.layers.41.linear_attn.in_proj_a","model.layers.41.linear_attn.in_proj_b","model.layers.42.linear_attn.in_proj_a","model.layers.42.linear_attn.in_proj_b","model.layers.44.linear_attn.in_proj_a","model.layers.44.linear_attn.in_proj_b","model.layers.45.linear_attn.in_proj_a","model.layers.45.linear_attn.in_proj_b","model.layers.46.linear_attn.in_proj_a","model.layers.46.linear_attn.in_proj_b","model.layers.48.linear_attn.in_proj_a","model.layers.48.linear_attn.in_proj_b","model.layers.49.linear_attn.in_proj_a","model.layers.49.linear_attn.in_proj_b","model.layers.5.linear_attn.in_proj_a","model.layers.5.linear_attn.in_proj_b","model.layers.50.linear_attn.in_proj_a","model.layers.50.linear_attn.in_proj_b","model.layers.52.linear_attn.in_proj_a","model.layers.52.linear_attn.in_proj_b","model.layers.53.linear_attn.in_proj_a","model.layers.53.linear_attn.in_proj_b","model.layers.54.linear_attn.in_proj_a","model.layers.54.linear_attn.in_proj_b","model.layers.56.linear_attn.in_proj_a","model.layers.56.linear_attn.in_proj_b","model.layers.57.linear_attn.in_proj_a","model.layers.57.linear_attn.in_proj_b","model.layers.58.linear_attn.in_proj_a","model.layers.58.linear_attn.in_proj_b","model.layers.6.linear_attn.in_proj_a","model.layers.6.linear_attn.in_proj_b","model.layers.60.linear_attn.in_proj_a","model.layers.60.linear_attn.in_proj_b","model.layers.61.linear_attn.in_proj_a","model.layers.61.linear_attn.in_proj_b","model.layers.62.linear_attn.in_proj_a","model.layers.62.linear_attn.in_proj_b","model.layers.8.linear_attn.in_proj_a","model.layers.8.linear_attn.in_proj_b","model.layers.9.linear_attn.in_proj_a","model.layers.9.linear_attn.in_proj_b","lm_head"],"kv_cache_scheme":null,"quant_method":"compressed-tensors","quantization_status":"compressed","sparsity_config":{},"transform_config":{},"version":"0.18.0"}}