Instructions to use jdopensource/JoyAI-LLM-Flash-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jdopensource/JoyAI-LLM-Flash-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="jdopensource/JoyAI-LLM-Flash-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jdopensource/JoyAI-LLM-Flash-FP8", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jdopensource/JoyAI-LLM-Flash-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jdopensource/JoyAI-LLM-Flash-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jdopensource/JoyAI-LLM-Flash-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jdopensource/JoyAI-LLM-Flash-FP8

SGLang

How to use jdopensource/JoyAI-LLM-Flash-FP8 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 "jdopensource/JoyAI-LLM-Flash-FP8" \
    --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": "jdopensource/JoyAI-LLM-Flash-FP8",
		"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 "jdopensource/JoyAI-LLM-Flash-FP8" \
        --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": "jdopensource/JoyAI-LLM-Flash-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jdopensource/JoyAI-LLM-Flash-FP8 with Docker Model Runner:
```
docker model run hf.co/jdopensource/JoyAI-LLM-Flash-FP8
```

JoyAI-LLM-Flash-FP8 / mergekit_config.yml

Mingke977

Add files using upload-large-folder tool

13fdcbe verified about 2 months ago

raw

history blame contribute delete

675 Bytes

	base_model: /root/myCodeLab/host/downloads/models/40Bra
	dtype: float32
	merge_method: dare_linear
	modules:
	default:
	slices:
	- sources:
	- layer_range: [0, 40]
	model: /root/myCodeLab/host/downloads/models/40Bra
	- layer_range: [0, 40]
	model: /root/myCodeLab/host/verl/ckpts/40bra_k8s_single_domain/40bra_k8s_16node_sd_c362_20260327_205644_unknown/global_step_50/actor/huggingface
	parameters:
	density: 1.0
	weight:
	- filter: .mlp.gate.
	value: 0.0
	- value: 0.5
	- sources:
	- layer_range: [40, 41]
	model: /root/myCodeLab/host/downloads/models/40Bra
	out_dtype: bfloat16