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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
llama cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
llama cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Use Docker

docker model run hf.co/Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

LM Studio
Jan

vLLM

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Ollama
How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Ollama:
```
ollama run hf.co/Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
```
Unsloth Desktop

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Run and chat with the model

lemonade run user.Solar-Open2-250B-Mixed-Quant-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Solar-Open2-250B-Mixed-Quant-GGUF / architecture.json

Baekpica

Add Solar architecture contract

cd504d0 verified 29 days ago

Raw

History Blame Contribute Delete

4.51 kB

	{
	"architecture": "solar_open2",
	"buffer_values": 15360,
	"config_sha256": "fb6428ba165af1ace1d98f9170f6bafce061347593a94bd16b4b8aa3d6fe09f9",
	"family_tensor_counts": {
	"gqa_projection": 60,
	"kda_matrix_projection": 324,
	"kda_small_control_norm_conv": 216,
	"lm_head": 1,
	"norm": 97,
	"routed_expert_down": 15360,
	"routed_expert_gate": 15360,
	"routed_expert_up": 15360,
	"router_control": 96,
	"shared_expert": 144,
	"token_embedding": 1
	},
	"gqa": {
	"head_dim": 128,
	"kv_heads": 8,
	"output_gate": true,
	"query_heads": 64,
	"use_rope": false
	},
	"gqa_layers": [
	0,
	4,
	8,
	12,
	16,
	20,
	24,
	28,
	32,
	36,
	40,
	44
	],
	"kda": {
	"allow_negative_eigenvalue": true,
	"gate_equation": "g=-exp(A_log)*softplus(g_raw+dt_bias), clamped at -5",
	"head_dim": 128,
	"heads": 64,
	"short_conv_kernel": 4,
	"source": "upstageAI/transformers modular_solar_open2.py",
	"state_equation": "S_t=exp(g_t)S_(t-1)+k_t(beta_t(v_t-S_decay^Tk_t))^T",
	"use_full_proj": false
	},
	"kda_layers": [
	1,
	2,
	3,
	5,
	6,
	7,
	9,
	10,
	11,
	13,
	14,
	15,
	17,
	18,
	19,
	21,
	22,
	23,
	25,
	26,
	27,
	29,
	30,
	31,
	33,
	34,
	35,
	37,
	38,
	39,
	41,
	42,
	43,
	45,
	46,
	47
	],
	"layer_schedule": [
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA",
	"GQA",
	"KDA",
	"KDA",
	"KDA"
	],
	"layers": 48,
	"moe": {
	"normalize_topk_weights": true,
	"routed_experts": 320,
	"routed_scaling_factor": 1.0,
	"routed_width": 1280,
	"router_activation": "sigmoid",
	"shared_experts": 1,
	"top_k": 8
	},
	"normalized_tensor_patterns": {
	"lm_head.weight": 1,
	"model.embed_tokens.weight": 1,
	"model.layers.{layer}.input_layernorm.weight": 48,
	"model.layers.{layer}.mlp.experts.{expert}.down_proj.weight": 15360,
	"model.layers.{layer}.mlp.experts.{expert}.gate_proj.weight": 15360,
	"model.layers.{layer}.mlp.experts.{expert}.up_proj.weight": 15360,
	"model.layers.{layer}.mlp.gate.e_score_correction_bias": 48,
	"model.layers.{layer}.mlp.gate.weight": 48,
	"model.layers.{layer}.mlp.shared_experts.down_proj.weight": 48,
	"model.layers.{layer}.mlp.shared_experts.gate_proj.weight": 48,
	"model.layers.{layer}.mlp.shared_experts.up_proj.weight": 48,
	"model.layers.{layer}.post_attention_layernorm.weight": 48,
	"model.layers.{layer}.self_attn.A_log": 36,
	"model.layers.{layer}.self_attn.b_proj.weight": 36,
	"model.layers.{layer}.self_attn.dt_bias": 36,
	"model.layers.{layer}.self_attn.f_a_proj.weight": 36,
	"model.layers.{layer}.self_attn.f_b_proj.weight": 36,
	"model.layers.{layer}.self_attn.g_a_proj.weight": 36,
	"model.layers.{layer}.self_attn.g_b_proj.weight": 36,
	"model.layers.{layer}.self_attn.g_proj.weight": 12,
	"model.layers.{layer}.self_attn.k_conv1d.weight": 36,
	"model.layers.{layer}.self_attn.k_proj.weight": 48,
	"model.layers.{layer}.self_attn.o_norm.weight": 36,
	"model.layers.{layer}.self_attn.o_proj.weight": 48,
	"model.layers.{layer}.self_attn.q_conv1d.weight": 36,
	"model.layers.{layer}.self_attn.q_proj.weight": 48,
	"model.layers.{layer}.self_attn.v_conv1d.weight": 36,
	"model.layers.{layer}.self_attn.v_proj.weight": 48,
	"model.norm.weight": 1
	},
	"schema_version": 1,
	"source": {
	"repo": "upstage/Solar-Open2-250B",
	"revision": "9190fbe63a2ad8e17fc766ccceb36de7c66f004b"
	},
	"source_dtype_counts": {
	"BF16": 46971,
	"F32": 48
	},
	"stored_values": 250287810304,
	"tensor_count": 47019,
	"tensor_header_sha256": "97281a0595ceeeec8c7579b8a384b9d5c35a4e5956e16b1b96cb690bd63c7f58",
	"trainable_parameters": 250287794944,
	"validation": {
	"errors": [],
	"ok": true,
	"warnings": [
	"pilot projection 97.76 GiB exceeds the 92 GiB artifact gate; pilot is an inventory/loadability artifact and must not be published as the capacity candidate"
	]
	}
	}