Instructions to use RayNene/Trilex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RayNene/Trilex with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RayNene/Trilex")
model = AutoModelForCausalLM.from_pretrained("RayNene/Trilex")
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 RayNene/Trilex with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RayNene/Trilex

SGLang

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

Docker Model Runner
How to use RayNene/Trilex with Docker Model Runner:
```
docker model run hf.co/RayNene/Trilex
```

Trilex / config.json

RayNene

Upload folder using huggingface_hub

09740de verified about 18 hours ago

Raw

History Blame Contribute Delete

3.74 kB

	{
	"architectures": [
	"Llama4ForCausalLM"
	],
	"attention_bias": false,
	"attention_chunk_size": 8192,
	"attention_dropout": 0.0,
	"attn_scale": 0.1,
	"attn_temperature_tuning": true,
	"bos_token_id": 200000,
	"cache_implementation": "hybrid",
	"dtype": "bfloat16",
	"eos_token_id": 200008,
	"floor_scale": 8192,
	"for_llm_compressor": false,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"interleave_moe_layer_step": 1,
	"intermediate_size": 8192,
	"intermediate_size_mlp": 16384,
	"layer_types": [
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention"
	],
	"max_position_embeddings": 10485760,
	"model_type": "llama4_text",
	"moe_layers": [
	0,
	1,
	2,
	3,
	4,
	5,
	6,
	7,
	8,
	9,
	10,
	11,
	12,
	13,
	14,
	15,
	16,
	17,
	18,
	19,
	20,
	21,
	22,
	23,
	24,
	25,
	26,
	27,
	28,
	29,
	30,
	31,
	32,
	33,
	34,
	35,
	36,
	37,
	38,
	39,
	40,
	41,
	42,
	43,
	44,
	45,
	46,
	47
	],
	"no_rope_layer_interval": 4,
	"no_rope_layers": [
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0
	],
	"num_attention_heads": 40,
	"num_experts_per_tok": 1,
	"num_hidden_layers": 48,
	"num_key_value_heads": 8,
	"num_local_experts": 16,
	"output_router_logits": false,
	"pad_token_id": 200018,
	"quantization_config": {
	"_load_in_4bit": true,
	"_load_in_8bit": false,
	"bnb_4bit_compute_dtype": "bfloat16",
	"bnb_4bit_quant_storage": "bfloat16",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": false,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": null,
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"factor": 16.0,
	"high_freq_factor": 1.0,
	"low_freq_factor": 1.0,
	"original_max_position_embeddings": 8192,
	"rope_theta": 500000.0,
	"rope_type": "llama3"
	},
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"tie_word_embeddings": false,
	"transformers_version": "5.10.1",
	"use_cache": false,
	"use_qk_norm": true,
	"vocab_size": 202048,
	"torch_dtype": "bfloat16"
	}