Instructions to use upstage/Solar-Open2-250B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use upstage/Solar-Open2-250B with Transformers:

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

pipe = pipeline("text-generation", model="upstage/Solar-Open2-250B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("upstage/Solar-Open2-250B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use upstage/Solar-Open2-250B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "upstage/Solar-Open2-250B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "upstage/Solar-Open2-250B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/upstage/Solar-Open2-250B

SGLang

How to use upstage/Solar-Open2-250B 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 "upstage/Solar-Open2-250B" \
    --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": "upstage/Solar-Open2-250B",
		"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 "upstage/Solar-Open2-250B" \
        --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": "upstage/Solar-Open2-250B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use upstage/Solar-Open2-250B with Docker Model Runner:
```
docker model run hf.co/upstage/Solar-Open2-250B
```

Solar-Open2-250B / config.json

SSON9

Release Solar Open2 250B

8d1dda5 verified 1 day ago

Raw

History Blame Contribute Delete

1.26 kB

	{
	"model_type": "solar_open2",
	"architectures": [
	"SolarOpen2ForCausalLM"
	],
	"pad_token_id": 2,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"partial_rotary_factor": 1.0,
	"linear_attn_config": {
	"short_conv_kernel_size": 4,
	"head_dim": 128,
	"num_heads": 64,
	"num_kv_heads": null
	},
	"hidden_size": 4096,
	"num_hidden_layers": 48,
	"num_attention_heads": 64,
	"head_dim": 128,
	"num_key_value_heads": 8,
	"vocab_size": 196608,
	"intermediate_size": 10240,
	"moe_intermediate_size": 1280,
	"rms_norm_eps": 1e-05,
	"rope_theta": 10000,
	"tie_word_embeddings": false,
	"max_position_embeddings": 1048576,
	"first_k_dense_replace": 0,
	"use_rope": false,
	"gqa_interval": 3,
	"gqa_layers": [
	0,
	4,
	8,
	12,
	16,
	20,
	24,
	28,
	32,
	36,
	40,
	44
	],
	"use_gqa_gate": true,
	"kda_use_full_proj": false,
	"kda_allow_neg_eigval": true,
	"n_routed_experts": 320,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"routed_scaling_factor": 1.0,
	"num_experts_per_tok": 8,
	"torch_dtype": "bfloat16",
	"transformers_version": "5.5.4"
	}