Instructions to use miceworks/Mark-Engineer-302M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use miceworks/Mark-Engineer-302M 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 miceworks/Mark-Engineer-302M:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf miceworks/Mark-Engineer-302M:IQ4_NL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf miceworks/Mark-Engineer-302M:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf miceworks/Mark-Engineer-302M:IQ4_NL

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 miceworks/Mark-Engineer-302M:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf miceworks/Mark-Engineer-302M:IQ4_NL

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 miceworks/Mark-Engineer-302M:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf miceworks/Mark-Engineer-302M:IQ4_NL

Use Docker

docker model run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL

Llama new
LM Studio
Jan

vLLM

How to use miceworks/Mark-Engineer-302M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "miceworks/Mark-Engineer-302M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "miceworks/Mark-Engineer-302M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL

Ollama
How to use miceworks/Mark-Engineer-302M with Ollama:
```
ollama run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL
```
Unsloth Desktop
Docker Model Runner
How to use miceworks/Mark-Engineer-302M with Docker Model Runner:
```
docker model run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL
```

Lemonade

How to use miceworks/Mark-Engineer-302M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull miceworks/Mark-Engineer-302M:IQ4_NL

Run and chat with the model

lemonade run user.Mark-Engineer-302M-IQ4_NL

List all available models

lemonade list

Atomic Chat

miceworks commited on about 7 hours ago

Commit

231feba

verified ·

1 Parent(s): 94f326e

fix: add config.json specifying exact parameter count

Browse files

Files changed (1) hide show

config.json +38 -0

config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "architectures": [
+    "MarkForCausalLM"
+  ],
+  "model_type": "mark",
+  "model_name": "Mark Engineer 300M",
+  "model_version": "1.0.0",
+  "total_parameters": 302019848,
+  "active_parameters_per_token": "110M (padrao) a 165M (top-4)",
+  "vocab_size": 4311,
+  "hidden_size": 1024,
+  "intermediate_size": 3072,
+  "num_hidden_layers": 8,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 4,
+  "use_mla": true,
+  "q_lora_rank": 512,
+  "kv_lora_rank": 256,
+  "qk_rope_head_dim": 32,
+  "v_head_dim": 64,
+  "n_routed_experts": 16,
+  "n_shared_experts": 1,
+  "num_experts_per_tok": 2,
+  "moe_intermediate_size": 1536,
+  "recursive_depth_loops": 2,
+  "mtp_depth": 1,
+  "max_position_embeddings": 4096,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "quantization": "IQ4_NL",
+  "download": {
+    "gguf_url": "https://github.com/thu12dta3/Mark-AI/releases/download/v1.0.0-302m/mark_engineer_302m.gguf",
+    "pt_url": "https://github.com/thu12dta3/Mark-AI/releases/download/v1.0.0-302m/mark_engineer_302m_iq4_nl.pt",
+    "sha256": "daf05dd0dab4fc90f620d959cb6e5731c49b3f3c4ddce0ff28765e0751075fd9"
+  }
+}