Instructions to use hf-internal-testing/HYV3-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/HYV3-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/HYV3-tiny-random")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/HYV3-tiny-random")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/HYV3-tiny-random")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/HYV3-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-internal-testing/HYV3-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/HYV3-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hf-internal-testing/HYV3-tiny-random

SGLang

How to use hf-internal-testing/HYV3-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 "hf-internal-testing/HYV3-tiny-random" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/HYV3-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "hf-internal-testing/HYV3-tiny-random" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/HYV3-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/HYV3-tiny-random with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/HYV3-tiny-random
```

HYV3-tiny-random

File size: 1,062 Bytes

0a0a3e3

{
  "architectures": [
    "HYV3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": null,
  "dtype": "bfloat16",
  "enable_moe_fp32_combine": true,
  "eos_token_id": null,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 768,
  "initializer_range": 0.006,
  "intermediate_size": 2048,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "mlp_layer_types": [
    "dense",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse"
  ],
  "model_type": "hy_v3",
  "moe_intermediate_size": 512,
  "num_attention_heads": 12,
  "num_experts": 16,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 8,
  "num_key_value_heads": 4,
  "num_shared_experts": 1,
  "output_router_logits": false,
  "pad_token_id": null,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 11158840.0,
    "rope_type": "default"
  },
  "router_scaling_factor": 2.826,
  "tie_word_embeddings": false,
  "transformers_version": "5.6.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}