Instructions to use TroyDoesAI/BlackSheep-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TroyDoesAI/BlackSheep-4B with Transformers:

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

pipe = pipeline("text-generation", model="TroyDoesAI/BlackSheep-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TroyDoesAI/BlackSheep-4B")
model = AutoModelForCausalLM.from_pretrained("TroyDoesAI/BlackSheep-4B")
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 TroyDoesAI/BlackSheep-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TroyDoesAI/BlackSheep-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TroyDoesAI/BlackSheep-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TroyDoesAI/BlackSheep-4B

SGLang

How to use TroyDoesAI/BlackSheep-4B 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 "TroyDoesAI/BlackSheep-4B" \
    --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": "TroyDoesAI/BlackSheep-4B",
		"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 "TroyDoesAI/BlackSheep-4B" \
        --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": "TroyDoesAI/BlackSheep-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TroyDoesAI/BlackSheep-4B with Docker Model Runner:
```
docker model run hf.co/TroyDoesAI/BlackSheep-4B
```

TroyDoesAI commited on Jul 7, 2024

Commit

8c5cf72

verified ·

1 Parent(s): 847a06e

Delete added_tokens.json

Browse files

Files changed (1) hide show

added_tokens.json +0 -40

added_tokens.json DELETED Viewed

@@ -1,40 +0,0 @@
-{
-  "<|/code|>": 32014,
-  "<|/data|>": 32033,
-  "<|/inst|>": 32037,
-  "<|/query|>": 32031,
-  "<|/sys|>": 32035,
-  "<|assistant_mask|>": 32017,
-  "<|assistant|>": 32001,
-  "<|calc|>": 32012,
-  "<|code|>": 32013,
-  "<|continue|>": 32009,
-  "<|data|>": 32032,
-  "<|diff_marker|>": 32025,
-  "<|disc_sep|>": 32029,
-  "<|disc_start|>": 32028,
-  "<|disc_thread|><|query|>": 32030,
-  "<|endoftext|>": 32000,
-  "<|end|>": 32007,
-  "<|fim_middle|>": 32021,
-  "<|fim_prefix|>": 32020,
-  "<|fim_suffix|>": 32022,
-  "<|function_call|>": 32005,
-  "<|function_list|>": 32011,
-  "<|function_output|>": 32003,
-  "<|ghissue|>": 32026,
-  "<|ghreview|>": 32027,
-  "<|inst|>": 32036,
-  "<|ipynb_marker|>": 32024,
-  "<|message|>": 32019,
-  "<|meta_start|>": 32023,
-  "<|raw|>": 32008,
-  "<|resource|>": 32016,
-  "<|start|>": 32018,
-  "<|step|>": 32002,
-  "<|summary|>": 32015,
-  "<|system|>": 32006,
-  "<|sys|>": 32034,
-  "<|tag|>": 32004,
-  "<|user|>": 32010
-}