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

Libraries

How to use cyrilvallez/test_remote_code_dummy_llama with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cyrilvallez/test_remote_code_dummy_llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/cyrilvallez/test_remote_code_dummy_llama

SGLang

How to use cyrilvallez/test_remote_code_dummy_llama 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 "cyrilvallez/test_remote_code_dummy_llama" \
    --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": "cyrilvallez/test_remote_code_dummy_llama",
		"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 "cyrilvallez/test_remote_code_dummy_llama" \
        --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": "cyrilvallez/test_remote_code_dummy_llama",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

cyrilvallez HF Staff commited on 10 days ago

Commit

bb53451

verified ·

1 Parent(s): bc77d93

Update modeling_dummy_llama.py

Browse files

Files changed (1) hide show

modeling_dummy_llama.py +1 -1

modeling_dummy_llama.py CHANGED Viewed

@@ -636,7 +636,7 @@ class KwargsForCausalLM(FlashAttentionKwargs): ...
 class DummyLlamaForCausalLM(DummyLlamaPreTrainedModel, GenerationMixin):
-    _tied_weights_keys = {"lm_head.weight": "embed_tokens.weight"}
     _tp_plan = {"lm_head": "colwise_rep"}
     def __init__(self, config):

 class DummyLlamaForCausalLM(DummyLlamaPreTrainedModel, GenerationMixin):
+    _tied_weights_keys = {"lm_head.weight": "model.embed_tokens.weight"}
     _tp_plan = {"lm_head": "colwise_rep"}
     def __init__(self, config):