Instructions to use intrect/VELA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use intrect/VELA with Transformers:

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

pipe = pipeline("text-generation", model="intrect/VELA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("intrect/VELA")
model = AutoModelForCausalLM.from_pretrained("intrect/VELA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use intrect/VELA with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="intrect/VELA",
	filename="vela-dpo-v6-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

MLX

How to use intrect/VELA with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("intrect/VELA")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use intrect/VELA with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf intrect/VELA:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf intrect/VELA:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf intrect/VELA:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf intrect/VELA:Q4_K_M

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 intrect/VELA:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf intrect/VELA:Q4_K_M

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 intrect/VELA:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf intrect/VELA:Q4_K_M

Use Docker

docker model run hf.co/intrect/VELA:Q4_K_M

LM Studio
Jan

vLLM

How to use intrect/VELA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/intrect/VELA:Q4_K_M

SGLang

How to use intrect/VELA 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 "intrect/VELA" \
    --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": "intrect/VELA",
		"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 "intrect/VELA" \
        --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": "intrect/VELA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use intrect/VELA with Ollama:
```
ollama run hf.co/intrect/VELA:Q4_K_M
```

Unsloth Studio new

How to use intrect/VELA with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for intrect/VELA to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for intrect/VELA to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for intrect/VELA to start chatting

Pi new

How to use intrect/VELA with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "intrect/VELA"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "intrect/VELA"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use intrect/VELA with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "intrect/VELA"

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 intrect/VELA

Run Hermes

hermes

MLX LM

How to use intrect/VELA with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "intrect/VELA"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "intrect/VELA"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "intrect/VELA",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use intrect/VELA with Docker Model Runner:
```
docker model run hf.co/intrect/VELA:Q4_K_M
```

Lemonade

How to use intrect/VELA with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull intrect/VELA:Q4_K_M

Run and chat with the model

lemonade run user.VELA-Q4_K_M

List all available models

lemonade list

intrect commited on Apr 1

Commit

de3e104

verified ·

1 Parent(s): 4043357

data: add raw benchmark results JSON (KMMLU + HAE-RAE, 3-model comparison)

Browse files

Files changed (1) hide show

benchmarks/benchmark_comparison_20260401.json +120 -0

benchmarks/benchmark_comparison_20260401.json ADDED Viewed

	@@ -0,0 +1,120 @@

+{
+  "benchmark_info": {
+    "date": "2026-04-01",
+    "framework": "lm-evaluation-harness 0.4.9.2",
+    "inference": "llama.cpp (llama-server b8330)",
+    "hardware": "Apple M1 Max 32GB",
+    "quantization": "Q4_K_M",
+    "n_shot": 0,
+    "tasks": "KMMLU direct (10 subjects) + HAE-RAE (5 subtasks)",
+    "method": "generate_until with regex extraction"
+  },
+  "models": {
+    "vela-dpo-v6": {
+      "full_name": "VELA DPO v6 (Qwen2.5-7B + SFT + DPO v6)",
+      "file": "vela-dpo-v6-q4km.gguf",
+      "size_gb": 4.4
+    },
+    "qwen2.5-7b-instruct": {
+      "full_name": "Qwen2.5-7B-Instruct (baseline)",
+      "file": "qwen2.5-7b-instruct-q4_k_m-00001-of-00002.gguf",
+      "size_gb": 4.4
+    },
+    "exaone-3.5-7.8b": {
+      "full_name": "EXAONE-3.5-7.8B-Instruct",
+      "file": "EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf",
+      "size_gb": 4.4
+    }
+  },
+  "kmmlu": {
+    "accounting": {
+      "vela_dpo_v6": 0.38,
+      "qwen25_7b": 0.33,
+      "exaone_35_7_8b": 0.42
+    },
+    "computer_science": {
+      "vela_dpo_v6": 0.737,
+      "qwen25_7b": 0.697,
+      "exaone_35_7_8b": 0.697
+    },
+    "economics": {
+      "vela_dpo_v6": 0.454,
+      "qwen25_7b": 0.477,
+      "exaone_35_7_8b": 0.515
+    },
+    "korean_history": {
+      "vela_dpo_v6": 0.31,
+      "qwen25_7b": 0.29,
+      "exaone_35_7_8b": 0.22
+    },
+    "law": {
+      "vela_dpo_v6": 0.434,
+      "qwen25_7b": 0.461,
+      "exaone_35_7_8b": 0.499
+    },
+    "management": {
+      "vela_dpo_v6": 0.54,
+      "qwen25_7b": 0.552,
+      "exaone_35_7_8b": 0.573
+    },
+    "marketing": {
+      "vela_dpo_v6": 0.757,
+      "qwen25_7b": 0.725,
+      "exaone_35_7_8b": 0.756
+    },
+    "math": {
+      "vela_dpo_v6": 0.33,
+      "qwen25_7b": 0.337,
+      "exaone_35_7_8b": 0.277
+    },
+    "political_science_and_sociology": {
+      "vela_dpo_v6": 0.49,
+      "qwen25_7b": 0.493,
+      "exaone_35_7_8b": 0.56
+    },
+    "psychology": {
+      "vela_dpo_v6": 0.392,
+      "qwen25_7b": 0.393,
+      "exaone_35_7_8b": 0.457
+    }
+  },
+  "haerae": {
+    "general_knowledge": {
+      "vela_dpo_v6": 0.4375,
+      "qwen25_7b": 0.4205,
+      "exaone_35_7_8b": 0.4432
+    },
+    "history": {
+      "vela_dpo_v6": 0.4574,
+      "qwen25_7b": 0.4255,
+      "exaone_35_7_8b": 0.7766
+    },
+    "loan_words": {
+      "vela_dpo_v6": 0.4852,
+      "qwen25_7b": 0.574,
+      "exaone_35_7_8b": 0.8107
+    },
+    "rare_words": {
+      "vela_dpo_v6": 0.6988,
+      "qwen25_7b": 0.684,
+      "exaone_35_7_8b": 0.7877
+    },
+    "standard_nomenclature": {
+      "vela_dpo_v6": 0.6471,
+      "qwen25_7b": 0.6601,
+      "exaone_35_7_8b": 0.719
+    }
+  },
+  "summary": {
+    "kmmlu_avg": {
+      "vela_dpo_v6": 0.482,
+      "qwen25_7b": 0.476,
+      "exaone_35_7_8b": 0.497
+    },
+    "haerae_avg": {
+      "vela_dpo_v6": 0.545,
+      "qwen25_7b": 0.553,
+      "exaone_35_7_8b": 0.707
+    }
+  }
+}