Instructions to use AuriLab/gpt-bi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AuriLab/gpt-bi with Transformers:

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

pipe = pipeline("text-generation", model="AuriLab/gpt-bi")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AuriLab/gpt-bi")
model = AutoModelForCausalLM.from_pretrained("AuriLab/gpt-bi")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AuriLab/gpt-bi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AuriLab/gpt-bi

SGLang

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

Docker Model Runner
How to use AuriLab/gpt-bi with Docker Model Runner:
```
docker model run hf.co/AuriLab/gpt-bi
```

ZeusCabanas commited on Feb 19, 2025

Commit

bf19f82

verified ·

1 Parent(s): 68d11c3

Upload tokenizer

Browse files

Files changed (5) hide show

added_tokens.json +2 -2
merges.txt +0 -0
tokenizer.json +0 -0
tokenizer_config.json +3 -3
vocab.json +0 -0

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "<|im_end|>": 50258,
-  "<|im_start|>": 50257
 }

 {
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
 }

merges.txt CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -9,7 +9,7 @@
       "single_word": false,
       "special": true
     },
-    "50257": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -17,7 +17,7 @@
       "single_word": false,
       "special": true
     },
-    "50258": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,

 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
+    "0": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "32000": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "32001": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,

vocab.json CHANGED Viewed

The diff for this file is too large to render. See raw diff