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

Libraries

How to use yujiepan/hrm-text-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/hrm-text-tiny-random")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/hrm-text-tiny-random")
model = AutoModelForCausalLM.from_pretrained("yujiepan/hrm-text-tiny-random", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yujiepan/hrm-text-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/hrm-text-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": "yujiepan/hrm-text-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yujiepan/hrm-text-tiny-random

SGLang

How to use yujiepan/hrm-text-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/hrm-text-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": "yujiepan/hrm-text-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 "yujiepan/hrm-text-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": "yujiepan/hrm-text-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

hrm-text-tiny-random / config.json

yujiepan

Upload folder using huggingface_hub

ab6ffa2 verified 4 months ago

Raw History Blame Contribute Delete

877 Bytes

	{
	"H_cycles": 2,
	"L_bp_cycles": [
	0,
	3
	],
	"L_cycles": 3,
	"architectures": [
	"HrmTextForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 6,
	"dtype": "bfloat16",
	"embedding_scale": 39.191835884530846,
	"eos_token_id": 11,
	"head_dim": 32,
	"hidden_act": "silu",
	"hidden_size": 8,
	"initializer_range": 0.025515518153991442,
	"intermediate_size": 64,
	"max_position_embeddings": 4096,
	"mlp_bias": false,
	"model_type": "hrm_text",
	"num_attention_heads": 4,
	"num_hidden_layers": 64,
	"num_key_value_heads": 4,
	"num_layers_per_stack": 8,
	"pad_token_id": 5,
	"prefix_lm": true,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.9.0",
	"use_cache": true,
	"vocab_size": 65536
	}