Instructions to use arcee-ai/Patent-Instruct-Extended with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Patent-Instruct-Extended with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/Patent-Instruct-Extended")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Patent-Instruct-Extended")
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Patent-Instruct-Extended", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arcee-ai/Patent-Instruct-Extended with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/Patent-Instruct-Extended"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Patent-Instruct-Extended",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arcee-ai/Patent-Instruct-Extended

SGLang

How to use arcee-ai/Patent-Instruct-Extended 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 "arcee-ai/Patent-Instruct-Extended" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Patent-Instruct-Extended",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "arcee-ai/Patent-Instruct-Extended" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Patent-Instruct-Extended",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arcee-ai/Patent-Instruct-Extended with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Patent-Instruct-Extended
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Patent-Instruct-Extended

Patent-Instruct-Extended is an extension of the following models using the passthrough method and mergekit:

arcee-ai/Patent-Instruct-7b

🧩 Configuration

  slices:
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 0
          - 4
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 2
          - 4
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 4
          - 8
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 6
          - 8
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 8
          - 12
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 10
          - 12
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 12
          - 16
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 14
          - 16
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 16
          - 20
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 18
          - 20
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 20
          - 24
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 22
          - 24
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 24
          - 28
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 26
          - 28
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 28
          - 32
  - sources:
      - model: arcee-ai/Patent-Instruct-7b
        layer_range:
          - 30
          - 32
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  merge_method: passthrough
  dtype: bfloat16

Downloads last month: 7

Safetensors

Model size

10B params

Tensor type

BF16

Model tree for arcee-ai/Patent-Instruct-Extended

Quantizations

1 model