Instructions to use psikosen/canopy-258m-r3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use psikosen/canopy-258m-r3 with Transformers:

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

pipe = pipeline("text-generation", model="psikosen/canopy-258m-r3", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("psikosen/canopy-258m-r3", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use psikosen/canopy-258m-r3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "psikosen/canopy-258m-r3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "psikosen/canopy-258m-r3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/psikosen/canopy-258m-r3

SGLang

How to use psikosen/canopy-258m-r3 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 "psikosen/canopy-258m-r3" \
    --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": "psikosen/canopy-258m-r3",
		"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 "psikosen/canopy-258m-r3" \
        --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": "psikosen/canopy-258m-r3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use psikosen/canopy-258m-r3 with Docker Model Runner:
```
docker model run hf.co/psikosen/canopy-258m-r3
```

canopy-258m-r3 / miniswardbower /artifacts /complex_chains_report.json

psikosen

Update to v3: Hybrid Input Protocol, 2x browser acceleration, and visual logging

7a54ec2 verified about 1 month ago

Raw History Blame Contribute Delete

995 Bytes

	[
	{
	"name": "Chain 1: E-Commerce Multi-Stage Cart & Checkout",
	"passed": true,
	"total_ms": 1774.41,
	"stages": [
	[
	"Stage 1: Configure & Add to Cart",
	383.6338601540774
	],
	[
	"Stage 2: Voucher & Checkout Open",
	676.8952731508762
	],
	[
	"Stage 3: Pipelined Form Submission",
	544.9664250481874
	]
	],
	"order_id": "CANOPY-ORD-508829",
	"screenshot": "/home/psikosen/canopy/miniswardbower/artifacts/complex_chains/chain1_ecommerce_receipt.png"
	},
	{
	"name": "Chain 2: ETL Bulk Filter & Modal Dispatch",
	"passed": true,
	"total_ms": 1313.81,
	"screenshot": "/home/psikosen/canopy/miniswardbower/artifacts/complex_chains/chain2_etl_dispatched.png"
	},
	{
	"name": "Chain 3: Spatial Grounding & Table Extraction",
	"passed": true,
	"total_ms": 452.98,
	"screenshot": "/home/psikosen/canopy/miniswardbower/artifacts/complex_chains/chain3_spatial_approved.png"
	}
	]