Instructions to use Agnes-AI/Agnes-2.5-Flash-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Agnes-AI/Agnes-2.5-Flash-Base with Transformers:

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

pipe = pipeline("text-generation", model="Agnes-AI/Agnes-2.5-Flash-Base", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Agnes-AI/Agnes-2.5-Flash-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Agnes-AI/Agnes-2.5-Flash-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Agnes-AI/Agnes-2.5-Flash-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Agnes-AI/Agnes-2.5-Flash-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Agnes-AI/Agnes-2.5-Flash-Base

SGLang

How to use Agnes-AI/Agnes-2.5-Flash-Base 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 "Agnes-AI/Agnes-2.5-Flash-Base" \
    --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": "Agnes-AI/Agnes-2.5-Flash-Base",
		"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 "Agnes-AI/Agnes-2.5-Flash-Base" \
        --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": "Agnes-AI/Agnes-2.5-Flash-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Agnes-AI/Agnes-2.5-Flash-Base with Docker Model Runner:
```
docker model run hf.co/Agnes-AI/Agnes-2.5-Flash-Base
```

Agnes-2.5-Flash-Base / serve.sh

Agnes-AI

Upload folder using huggingface_hub

e6b37e4 verified 2 days ago

Raw

History Blame Contribute Delete

816 Bytes

	#!/bin/bash
	# Agnes PFFN-FP8 serving entrypoint, pinned to lmsysorg/sglang:v0.5.16.
	#
	# Usage:
	# docker run --gpus all --shm-size 64g -p 30001:30002 \
	# -v /path/to/this/model:/model \
	# lmsysorg/sglang:v0.5.16 bash /model/serve.sh
	#
	# Extra sglang flags may be appended after serve.sh, e.g.:
	# ... bash /model/serve.sh --tp 4
	set -e
	MODEL_DIR="$(cd "$(dirname "$0")" && pwd)"
	SGL_PKG=/sgl-workspace/sglang/python/sglang

	# Overlay the Agnes support files onto the stock sglang package
	# (inside this container only; the model directory is never modified).
	cp -r "$MODEL_DIR/sglang_patch/srt" "$MODEL_DIR/sglang_patch/kernels" "$SGL_PKG/"

	exec sglang serve --model-path "$MODEL_DIR" --trust-remote-code --tp 8 \
	--context-length 1048576 --mem-fraction-static 0.90 \
	--host 0.0.0.0 --port 30002 "$@"