Instructions to use wordcab/llama-natural-instructions-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wordcab/llama-natural-instructions-13b with Transformers:

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

pipe = pipeline("text-generation", model="wordcab/llama-natural-instructions-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("wordcab/llama-natural-instructions-13b")
model = AutoModelForMultimodalLM.from_pretrained("wordcab/llama-natural-instructions-13b")

PEFT
How to use wordcab/llama-natural-instructions-13b with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wordcab/llama-natural-instructions-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wordcab/llama-natural-instructions-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wordcab/llama-natural-instructions-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/wordcab/llama-natural-instructions-13b

SGLang

How to use wordcab/llama-natural-instructions-13b 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 "wordcab/llama-natural-instructions-13b" \
    --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": "wordcab/llama-natural-instructions-13b",
		"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 "wordcab/llama-natural-instructions-13b" \
        --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": "wordcab/llama-natural-instructions-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use wordcab/llama-natural-instructions-13b with Docker Model Runner:
```
docker model run hf.co/wordcab/llama-natural-instructions-13b
```

chainyo commited on Apr 13, 2023

Commit

c34b258

1 Parent(s): 38a13e0

add generation config

Browse files

Files changed (1) hide show

README.md +7 -0

README.md CHANGED Viewed

@@ -139,6 +139,13 @@ prompt = generate_prompt(
 inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=2048)
 input_ids = inputs["input_ids"].to(model.device)
 with torch.no_grad():
     gen_outputs = model.generate(
         input_ids=input_ids,

 inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=2048)
 input_ids = inputs["input_ids"].to(model.device)
+generation_config = GenerationConfig(
+    temperature=0.2,
+    top_p=0.75,
+    top_k=40,
+    num_beams=4,
+)
 with torch.no_grad():
     gen_outputs = model.generate(
         input_ids=input_ids,