Instructions to use SSON9/solar-open2-tiny-dummy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SSON9/solar-open2-tiny-dummy with Transformers:

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

pipe = pipeline("text-generation", model="SSON9/solar-open2-tiny-dummy")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SSON9/solar-open2-tiny-dummy", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SSON9/solar-open2-tiny-dummy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SSON9/solar-open2-tiny-dummy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SSON9/solar-open2-tiny-dummy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SSON9/solar-open2-tiny-dummy

SGLang

How to use SSON9/solar-open2-tiny-dummy 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 "SSON9/solar-open2-tiny-dummy" \
    --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": "SSON9/solar-open2-tiny-dummy",
		"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 "SSON9/solar-open2-tiny-dummy" \
        --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": "SSON9/solar-open2-tiny-dummy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SSON9/solar-open2-tiny-dummy with Docker Model Runner:
```
docker model run hf.co/SSON9/solar-open2-tiny-dummy
```

solar-open2-tiny-dummy / config.json

SSON9

Add solar-open2 tiny dummy (random weights, CI integration test)

919b792 verified 19 days ago

Raw

History Blame Contribute Delete

1.67 kB

	{
	"architectures": [
	"SolarOpen2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"dtype": "bfloat16",
	"eos_token_id": 2,
	"first_k_dense_replace": 0,
	"gqa_interval": 3,
	"gqa_layers": null,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"initializer_range": 0.02,
	"intermediate_size": 512,
	"kda_allow_neg_eigval": true,
	"kda_gate_lower_bound": -5.0,
	"kda_use_full_proj": false,
	"layer_types": [
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention"
	],
	"linear_attn_config": {
	"head_dim": 128,
	"num_heads": 8,
	"num_kv_heads": null,
	"short_conv_kernel_size": 4
	},
	"max_position_embeddings": 4096,
	"model_type": "solar_open2",
	"moe_intermediate_size": 256,
	"n_group": 1,
	"n_routed_experts": 16,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 8,
	"num_experts_per_tok": 4,
	"num_hidden_layers": 12,
	"num_key_value_heads": 2,
	"pad_token_id": 2,
	"partial_rotary_factor": 1.0,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 1.0,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"routed_scaling_factor": 1.0,
	"tie_word_embeddings": false,
	"topk_group": 1,
	"transformers_version": "5.15.0.dev0",
	"use_cache": true,
	"use_gqa_gate": true,
	"use_gqa_gate_bias": false,
	"use_qk_norm": false,
	"use_rope": false,
	"vocab_size": 196608
	}