Instructions to use tiny-random/bailing-moe-v2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/bailing-moe-v2.5 with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/bailing-moe-v2.5", 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("tiny-random/bailing-moe-v2.5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/bailing-moe-v2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/bailing-moe-v2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/bailing-moe-v2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/bailing-moe-v2.5

SGLang

How to use tiny-random/bailing-moe-v2.5 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 "tiny-random/bailing-moe-v2.5" \
    --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": "tiny-random/bailing-moe-v2.5",
		"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 "tiny-random/bailing-moe-v2.5" \
        --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": "tiny-random/bailing-moe-v2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/bailing-moe-v2.5 with Docker Model Runner:
```
docker model run hf.co/tiny-random/bailing-moe-v2.5
```

yujiepan commited on Feb 13

Commit

bbdb4c5

verified ·

1 Parent(s): 842a1e2

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +3 -2
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -15,8 +15,8 @@ This tiny model is intended for debugging. It is randomly initialized using the
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import transformers
 transformers.utils.import_utils.is_torch_fx_available = transformers.utils.import_utils.is_torch_available
 model_id = "tiny-random/bailing-moe-v2.5"
@@ -41,6 +41,7 @@ from pathlib import Path
 import accelerate
 import torch
 from huggingface_hub import file_exists, hf_hub_download
 from transformers import (
     AutoConfig,
@@ -49,7 +50,6 @@ from transformers import (
     GenerationConfig,
     set_seed,
 )
-import transformers
 transformers.utils.import_utils.is_torch_fx_available = transformers.utils.import_utils.is_torch_available
 source_model_id = "inclusionAI/Ring-2.5-1T"
 save_folder = "/tmp/tiny-random/bailing-moe-v25"
@@ -98,6 +98,7 @@ with torch.no_grad():
     for name, p in sorted(model.named_parameters()):
         torch.nn.init.normal_(p, 0, 0.1)
         print(name, p.shape)
 model.save_pretrained(save_folder)
 print(model)
 with open(f"{save_folder}/config.json", "r", encoding='utf-8') as f:

 ```python
 import torch
 import transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 transformers.utils.import_utils.is_torch_fx_available = transformers.utils.import_utils.is_torch_available
 model_id = "tiny-random/bailing-moe-v2.5"
 import accelerate
 import torch
+import transformers
 from huggingface_hub import file_exists, hf_hub_download
 from transformers import (
     AutoConfig,
     GenerationConfig,
     set_seed,
 )
 transformers.utils.import_utils.is_torch_fx_available = transformers.utils.import_utils.is_torch_available
 source_model_id = "inclusionAI/Ring-2.5-1T"
 save_folder = "/tmp/tiny-random/bailing-moe-v25"
     for name, p in sorted(model.named_parameters()):
         torch.nn.init.normal_(p, 0, 0.1)
         print(name, p.shape)
+model.model.layers[1].mlp.gate.expert_bias = model.model.layers[1].mlp.gate.expert_bias.float()
 model.save_pretrained(save_folder)
 print(model)
 with open(f"{save_folder}/config.json", "r", encoding='utf-8') as f:

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4689d2bae0110253d4a2f2738e903faefce4873dcefd04e8929a08bf80f6f0bd
-size 6680608

 version https://git-lfs.github.com/spec/v1
+oid sha256:19a618643f76a64b5b7b204ca792355fa0c8c161e7586981e55d0d81caf34eb3
+size 6681112