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

Libraries

How to use yujiepan/hymba-tiny-random with Transformers:

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

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

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("yujiepan/hymba-tiny-random", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yujiepan/hymba-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/hymba-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/hymba-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yujiepan/hymba-tiny-random

SGLang

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

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

hymba-tiny-random / README.md

yujiepan

Upload folder using huggingface_hub

41f7583 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

2.16 kB

metadata

library_name: transformers
pipeline_tag: text-generation
inference: true
widget:
  - text: Hello!
    example_title: Hello world
    group: Python

This model is for debugging. It is randomly initialized with the config from nvidia/Hymba-1.5B-Instruct but is of smaller size.

Codes:

from huggingface_hub import create_repo, upload_folder
import os

import torch
import transformers
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, pipeline, set_seed

model_id = "nvidia/Hymba-1.5B-Instruct"
repo_id = "yujiepan/hymba-tiny-random"
save_path = f"/tmp/{repo_id}"

config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
config.conv_dim = {str(i): 32 for i in range(3)}
config.hidden_size = 16
config.intermediate_size = 32
config.num_attention_heads = 2
config.num_key_value_heads = 1
config.v_head_dim = 8
config.num_hidden_layers = 3

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
tokenizer.save_pretrained(save_path)

model = AutoModelForCausalLM.from_config(
    config, torch_dtype=torch.bfloat16, trust_remote_code=True,
)
model.generation_config = GenerationConfig.from_pretrained(
    model_id, trust_remote_code=True)

set_seed(42)
with torch.no_grad():
    for _, p in sorted(model.named_parameters()):
        torch.nn.init.uniform_(p, -0.2, 0.2)

model.save_pretrained(save_path)

prompt = 'Hello!'
messages = [
    {"role": "system", "content": "You are a helpful assistant."}
]
messages.append({"role": "user", "content": prompt})
tokenized_chat = tokenizer.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to('cuda')
outputs = model.cuda().generate(
    tokenized_chat,
    max_new_tokens=16,
    do_sample=False,
    temperature=0.7,
    use_cache=True,
)
input_length = tokenized_chat.shape[1]
response = tokenizer.decode(
    outputs[0][input_length:], skip_special_tokens=True)
print(f"Model response: {response}")

os.system(f"ls -alh {save_path}")
create_repo(repo_id, exist_ok=True)
upload_folder(repo_id=repo_id, folder_path=save_path)