Instructions to use tianleliphoebe/BREEN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tianleliphoebe/BREEN with Transformers:

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

pipe = pipeline("text-generation", model="tianleliphoebe/BREEN")
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("tianleliphoebe/BREEN", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tianleliphoebe/BREEN with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tianleliphoebe/BREEN

SGLang

How to use tianleliphoebe/BREEN 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 "tianleliphoebe/BREEN" \
    --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": "tianleliphoebe/BREEN",
		"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 "tianleliphoebe/BREEN" \
        --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": "tianleliphoebe/BREEN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tianleliphoebe/BREEN with Docker Model Runner:
```
docker model run hf.co/tianleliphoebe/BREEN
```

tianleliphoebe commited on Mar 24, 2025

Commit

b4162ea

verified ·

1 Parent(s): ca6f126

Upload config

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "checkpoints/BREEN",
   "add_binary_mask": true,
   "add_learnable_query": true,
   "aggregate_mask": true,
@@ -57,7 +57,7 @@
   "shared": false,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.45.1",
   "tune_mm_mlp_adapter": false,
   "use_cache": false,

 {
+  "_name_or_path": "/apdcephfs_jn/share_302244400/phoebetlli/EVE_moe/checkpoints/eve-qwen25-7B-fitu-instruct-imgexp-autoclip-add-cos-multi-concatre34-pretext-mask-addtext-agg-linear-sft4m-4n/checkpoint-16200",
   "add_binary_mask": true,
   "add_learnable_query": true,
   "aggregate_mask": true,
   "shared": false,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
   "tune_mm_mlp_adapter": false,
   "use_cache": false,