Instructions to use PatrickHaller/hgrn2_de_wiki with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PatrickHaller/hgrn2_de_wiki with Transformers:

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

pipe = pipeline("text-generation", model="PatrickHaller/hgrn2_de_wiki", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("PatrickHaller/hgrn2_de_wiki", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PatrickHaller/hgrn2_de_wiki with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PatrickHaller/hgrn2_de_wiki"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PatrickHaller/hgrn2_de_wiki",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PatrickHaller/hgrn2_de_wiki

SGLang

How to use PatrickHaller/hgrn2_de_wiki 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 "PatrickHaller/hgrn2_de_wiki" \
    --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": "PatrickHaller/hgrn2_de_wiki",
		"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 "PatrickHaller/hgrn2_de_wiki" \
        --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": "PatrickHaller/hgrn2_de_wiki",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PatrickHaller/hgrn2_de_wiki with Docker Model Runner:
```
docker model run hf.co/PatrickHaller/hgrn2_de_wiki
```

PatrickHaller commited on Sep 30, 2024

Commit

b17e664

verified ·

1 Parent(s): a78e114

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +35 -0

config.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "architectures": [
+    "HGRN2ForCausalLM"
+  ],
+  "attn_mode": "chunk",
+  "bos_token_id": 1,
+  "conv_size": 4,
+  "elementwise_affine": true,
+  "eos_token_id": 2,
+  "expand_ratio": 128,
+  "fuse_cross_entropy": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "hgrn2",
+  "norm_eps": 1e-06,
+  "num_heads": null,
+  "num_hidden_layers": 26,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.1",
+  "use_cache": true,
+  "use_lower_bound": true,
+  "use_short_conv": false,
+  "vocab_size": 32000,
+  "auto_map": {
+    "AutoConfig": "configuration_hgrn2.HGRN2Config",
+    "AutoModelForCausalLM": "modeling_hgrn2.HGRN2ForCausalLM",
+    "AutoModel": "modeling_hgrn2.HGRN2Model",
+    "AutoModelForSequenceClassification": "modeling_hgrn2.HGRN2ForSequenceClassification"
+  }
+}