Text Generation
Transformers
Safetensors
MLX
English
qwen2
servicenow
itsm
csdm
itom
delivery
solution-design
user-stories
business-analysis
qwen2.5
lora
sft
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use MainStack/marvy-1-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MainStack/marvy-1-14B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MainStack/marvy-1-14B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MainStack/marvy-1-14B") model = AutoModelForCausalLM.from_pretrained("MainStack/marvy-1-14B") 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]:])) - MLX
How to use MainStack/marvy-1-14B 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("MainStack/marvy-1-14B") 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) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- vLLM
How to use MainStack/marvy-1-14B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MainStack/marvy-1-14B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MainStack/marvy-1-14B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/MainStack/marvy-1-14B
- SGLang
How to use MainStack/marvy-1-14B 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 "MainStack/marvy-1-14B" \ --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": "MainStack/marvy-1-14B", "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 "MainStack/marvy-1-14B" \ --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": "MainStack/marvy-1-14B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Pi
How to use MainStack/marvy-1-14B with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "MainStack/marvy-1-14B"
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": "MainStack/marvy-1-14B" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use MainStack/marvy-1-14B 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 "MainStack/marvy-1-14B"
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 MainStack/marvy-1-14B
Run Hermes
hermes
- MLX LM
How to use MainStack/marvy-1-14B with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "MainStack/marvy-1-14B"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "MainStack/marvy-1-14B" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MainStack/marvy-1-14B", "messages": [ {"role": "user", "content": "Hello"} ] }' - Docker Model Runner
How to use MainStack/marvy-1-14B with Docker Model Runner:
docker model run hf.co/MainStack/marvy-1-14B
| # marvy-14B quick validation harness. | |
| # | |
| # Runs the task-coverage probes (Test 2 in VALIDATION.md) against any | |
| # OpenAI-compatible endpoint — LM Studio, mlx_lm server, vLLM, etc. — and prints | |
| # each artifact plus a lightweight heuristic PASS/FAIL on domain keywords. | |
| # | |
| # Usage: | |
| # bash validate.sh # defaults to LM Studio | |
| # BASE_URL=http://localhost:8080/v1 MODEL=marvy-14B bash validate.sh | |
| # API_KEY=xxx BASE_URL=https://... MODEL=MainStack/marvy-14B bash validate.sh | |
| set -uo pipefail | |
| BASE_URL="${BASE_URL:-http://localhost:1234/v1}" # LM Studio default | |
| MODEL="${MODEL:-marvy-14B}" | |
| API_KEY="${API_KEY:-lm-studio}" | |
| TEMP="${TEMP:-0.4}" | |
| MAXTOK="${MAXTOK:-700}" | |
| SYSTEM="You are a senior ServiceNow delivery consultant. You produce precise, implementation-grade artifacts: business analyses, requirements, solution design documents, user stories with acceptance criteria, test cases, and validation reviews. You favor out-of-the-box capabilities, cite concrete tables/plugins/sys_ids when relevant, and write in clear professional English." | |
| # probe | expected-keyword-regex (case-insensitive) for a heuristic pass | |
| PROMPTS=( | |
| "Write a user story with acceptance criteria for auto-escalating P1 incidents that breach a 15-minute response SLA.|as a.*i want.*so that|acceptance|sla" | |
| "Draft the Incident Management section of an SDD for a greenfield ITSM implementation. Include assignment rules and SLA design.|assignment|sla|incident" | |
| "Extract structured requirements (id, category, priority, target phase, success metric) from: replace email-based access requests with a catalog item routed for manager approval.|priority|requirement|catalog" | |
| "Write a test case for the story: Restrict the Assignment Group field on incidents to groups with the itil role.|pre-condition|step|expected|itil" | |
| "Validate this requirement against best practice and list follow-up questions: All incidents must auto-close after 3 days.|follow-up|risk|question" | |
| ) | |
| command -v jq >/dev/null 2>&1 || { echo "ERROR: jq is required (brew install jq)"; exit 1; } | |
| echo "Endpoint: $BASE_URL Model: $MODEL Temp: $TEMP" | |
| echo "============================================================" | |
| pass=0; total=0 | |
| for entry in "${PROMPTS[@]}"; do | |
| total=$((total+1)) | |
| prompt="${entry%%|*}" | |
| rest="${entry#*|}"; regex="$rest" | |
| payload=$(jq -n --arg m "$MODEL" --arg s "$SYSTEM" --arg p "$prompt" \ | |
| --argjson t "$TEMP" --argjson mx "$MAXTOK" \ | |
| '{model:$m,temperature:$t,max_tokens:$mx,messages:[{role:"system",content:$s},{role:"user",content:$p}]}') | |
| resp=$(curl -s "$BASE_URL/chat/completions" -H "Content-Type: application/json" \ | |
| -H "Authorization: Bearer $API_KEY" -d "$payload") | |
| content=$(echo "$resp" | jq -r '.choices[0].message.content // .error.message // "<<no response>>"') | |
| echo "" | |
| echo "### Probe $total: $prompt" | |
| echo "------------------------------------------------------------" | |
| echo "$content" | head -40 | |
| if echo "$content" | grep -iqE "$regex"; then | |
| echo ">>> heuristic: PASS" | |
| pass=$((pass+1)) | |
| else | |
| echo ">>> heuristic: REVIEW (expected pattern not matched: $regex)" | |
| fi | |
| echo "============================================================" | |
| done | |
| echo "" | |
| echo "Heuristic result: $pass/$total probes matched domain patterns." | |
| echo "Pass threshold: >= 4/5 with implementation-grade, ServiceNow-specific content." | |
| echo "Note: heuristics are a sanity check — read the outputs to judge true quality." | |