Instructions to use VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct")
model = AutoModelForCausalLM.from_pretrained("VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct

SGLang

How to use VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct 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 "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct" \
    --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": "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct",
		"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 "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct" \
        --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": "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct with Docker Model Runner:
```
docker model run hf.co/VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
```

DavidGF commited on Apr 29, 2024

Commit

37127c4

verified ·

1 Parent(s): 4a77598

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -334,15 +334,16 @@ Llama-3-SauerkrautLM-8b-Instruct  7.65625
 ```
 **German RAG LLM Evaluation**
 ```
 |                         Task                         |Version|Metric|Value|   |Stderr|
 |------------------------------------------------------|------:|------|----:|---|-----:|
-|all                                                   |       |acc   |0.905|±  |0.0086|
-|community:german_rag_eval:_average:0                  |       |acc   |0.905|±  |0.0086|
-|community:german_rag_eval:choose_context_by_question:0|      0|acc   |0.896|±  |0.0097|
-|community:german_rag_eval:choose_question_by_context:0|      0|acc   |0.826|±  |0.0120|
-|community:german_rag_eval:context_question_match:0    |      0|acc   |0.987|±  |0.0036|
-|community:german_rag_eval:question_answer_match:0     |      0|acc   |0.911|±  |0.0090|
 ```
 ## Disclaimer

 ```
 **German RAG LLM Evaluation**
+corrected result after FIX: https://github.com/huggingface/lighteval/pull/171
 ```
 |                         Task                         |Version|Metric|Value|   |Stderr|
 |------------------------------------------------------|------:|------|----:|---|-----:|
+|all                                                   |       |acc   |0.910|±  |0.0084|
+|community:german_rag_eval:_average:0                  |       |acc   |0.910|±  |0.0084|
+|community:german_rag_eval:choose_context_by_question:0|      0|acc   |0.928|±  |0.0082|
+|community:german_rag_eval:choose_question_by_context:0|      0|acc   |0.824|±  |0.0120|
+|community:german_rag_eval:context_question_match:0    |      0|acc   |0.982|±  |0.0042|
+|community:german_rag_eval:question_answer_match:0     |      0|acc   |0.906|±  |0.0092|
 ```
 ## Disclaimer