Instructions to use XHToken/Spark-X2.5-1.7B-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XHToken/Spark-X2.5-1.7B-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="XHToken/Spark-X2.5-1.7B-INT8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XHToken/Spark-X2.5-1.7B-INT8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XHToken/Spark-X2.5-1.7B-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XHToken/Spark-X2.5-1.7B-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XHToken/Spark-X2.5-1.7B-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XHToken/Spark-X2.5-1.7B-INT8

SGLang

How to use XHToken/Spark-X2.5-1.7B-INT8 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 "XHToken/Spark-X2.5-1.7B-INT8" \
    --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": "XHToken/Spark-X2.5-1.7B-INT8",
		"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 "XHToken/Spark-X2.5-1.7B-INT8" \
        --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": "XHToken/Spark-X2.5-1.7B-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XHToken/Spark-X2.5-1.7B-INT8 with Docker Model Runner:
```
docker model run hf.co/XHToken/Spark-X2.5-1.7B-INT8
```

Spark-X2.5-1.7B-INT8 / config.json

Flyingmarx

Upload 13 files

57060f8 verified 7 days ago

Raw

History Blame Contribute Delete

4.29 kB

	{
	"architectures": [
	"Spark2_5ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_spark.Spark2_5Config",
	"AutoModel": "modeling_spark.Spark2_5Model",
	"AutoModelForCausalLM": "modeling_spark.Spark2_5ForCausalLM"
	},
	"bos_token_id": 0,
	"dtype": "bfloat16",
	"eos_token_id": 1,
	"gate_attn_act_mode": "sigmoid",
	"head_dim": 256,
	"headwise_attn_output_gate": true,
	"hidden_act": "gelu",
	"hidden_size": 2048,
	"initializer_range": 0.0221,
	"intermediate_size": 6656,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 1048576,
	"mlp_bias": false,
	"model_type": "spark2_5",
	"num_attention_heads": 8,
	"num_hidden_layers": 28,
	"num_key_value_heads": 2,
	"pad_token_id": 2,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"full_attention": {
	"partial_rotary_factor": 0.25,
	"rope_theta": 5000000
	},
	"sliding_attention": {
	"partial_rotary_factor": 1.0,
	"rope_theta": 10000
	}
	},
	"sliding_window": 512,
	"tie_word_embeddings": true,
	"transformers_version": "4.57.1",
	"use_cache": true,
	"vocab_size": 131072,
	"quantization_config": {
	"version": "0.13.0",
	"quant_method": "compressed-tensors",
	"sparsity_config": {},
	"transform_config": {},
	"config_groups": {
	"group_0": {
	"targets": [
	"Linear"
	],
	"weights": {
	"num_bits": 8,
	"type": "int",
	"symmetric": true,
	"group_size": null,
	"strategy": "channel",
	"block_structure": null,
	"dynamic": false,
	"actorder": null,
	"scale_dtype": null,
	"zp_dtype": null,
	"observer": "minmax",
	"observer_kwargs": {}
	},
	"input_activations": {
	"num_bits": 8,
	"type": "int",
	"symmetric": true,
	"group_size": null,
	"strategy": "token",
	"block_structure": null,
	"dynamic": true,
	"actorder": null,
	"scale_dtype": null,
	"zp_dtype": null,
	"observer": null,
	"observer_kwargs": {}
	},
	"output_activations": null,
	"format": "int-quantized"
	}
	},
	"format": "int-quantized",
	"quantization_status": "compressed",
	"global_compression_ratio": null,
	"ignore": [
	"lm_head",
	"model.layers.0.self_attn.g_proj",
	"model.layers.1.self_attn.g_proj",
	"model.layers.10.self_attn.g_proj",
	"model.layers.11.self_attn.g_proj",
	"model.layers.12.self_attn.g_proj",
	"model.layers.13.self_attn.g_proj",
	"model.layers.14.self_attn.g_proj",
	"model.layers.15.self_attn.g_proj",
	"model.layers.16.self_attn.g_proj",
	"model.layers.17.self_attn.g_proj",
	"model.layers.18.self_attn.g_proj",
	"model.layers.19.self_attn.g_proj",
	"model.layers.2.self_attn.g_proj",
	"model.layers.20.self_attn.g_proj",
	"model.layers.21.self_attn.g_proj",
	"model.layers.22.self_attn.g_proj",
	"model.layers.23.self_attn.g_proj",
	"model.layers.24.self_attn.g_proj",
	"model.layers.25.self_attn.g_proj",
	"model.layers.26.self_attn.g_proj",
	"model.layers.27.self_attn.g_proj",
	"model.layers.3.self_attn.g_proj",
	"model.layers.4.self_attn.g_proj",
	"model.layers.5.self_attn.g_proj",
	"model.layers.6.self_attn.g_proj",
	"model.layers.7.self_attn.g_proj",
	"model.layers.8.self_attn.g_proj",
	"model.layers.9.self_attn.g_proj"
	],
	"kv_cache_scheme": null
	}
	}