Instructions to use yujiepan/llama-3-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/llama-3-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/llama-3-tiny-random")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/llama-3-tiny-random")
model = AutoModelForCausalLM.from_pretrained("yujiepan/llama-3-tiny-random")
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 yujiepan/llama-3-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/llama-3-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/llama-3-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yujiepan/llama-3-tiny-random

SGLang

How to use yujiepan/llama-3-tiny-random 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 "yujiepan/llama-3-tiny-random" \
    --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": "yujiepan/llama-3-tiny-random",
		"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 "yujiepan/llama-3-tiny-random" \
        --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": "yujiepan/llama-3-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yujiepan/llama-3-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/llama-3-tiny-random
```

yujiepan commited on Apr 27, 2024

Commit

5d8b95d

verified ·

1 Parent(s): 767d9d2

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -1

README.md CHANGED Viewed

@@ -19,11 +19,14 @@ import transformers
 import torch
 import os
 from huggingface_hub import create_repo, upload_folder
 source_model_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
 save_path = '/tmp/yujiepan/meta-llama-3-tiny-random'
 repo_id = 'yujiepan/meta-llama-3-tiny-random'
 config = transformers.AutoConfig.from_pretrained(
     source_model_id,
     trust_remote_code=True,
@@ -40,6 +43,10 @@ model = transformers.AutoModelForCausalLM.from_config(
     config,
     trust_remote_code=True,
 )
 model = model.to(torch.bfloat16)
 model.save_pretrained(save_path)
@@ -52,6 +59,8 @@ tokenizer.save_pretrained(save_path)
 model.float().generate(torch.tensor([[1, 2, 3]]).long(), max_length=16)
 os.system(f'ls -alh {save_path}')
 create_repo(repo_id, exist_ok=True)
-upload_folder(repo_id=repo_id, folder_path=save_path)
 ```

 import torch
 import os
 from huggingface_hub import create_repo, upload_folder
+import accelerate
 source_model_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
 save_path = '/tmp/yujiepan/meta-llama-3-tiny-random'
 repo_id = 'yujiepan/meta-llama-3-tiny-random'
+os.system(f'rm -rf {save_path}')
 config = transformers.AutoConfig.from_pretrained(
     source_model_id,
     trust_remote_code=True,
     config,
     trust_remote_code=True,
 )
+with accelerate.init_empty_weights():
+    model.generation_config = transformers.AutoModelForCausalLM.from_pretrained(source_model_id).generation_config
 model = model.to(torch.bfloat16)
 model.save_pretrained(save_path)
 model.float().generate(torch.tensor([[1, 2, 3]]).long(), max_length=16)
 os.system(f'ls -alh {save_path}')
+# os.system(f'rm -rf {save_path}/model.safetensors')
 create_repo(repo_id, exist_ok=True)
+upload_folder(repo_id='yujiepan/meta-llama-3-tiny-random', folder_path=save_path)
+upload_folder(repo_id='yujiepan/llama-3-tiny-random', folder_path=save_path)
 ```