Instructions to use openlm-research/open_llama_13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openlm-research/open_llama_13b with Transformers:

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

pipe = pipeline("text-generation", model="openlm-research/open_llama_13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openlm-research/open_llama_13b")
model = AutoModelForCausalLM.from_pretrained("openlm-research/open_llama_13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openlm-research/open_llama_13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openlm-research/open_llama_13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openlm-research/open_llama_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openlm-research/open_llama_13b

SGLang

How to use openlm-research/open_llama_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 "openlm-research/open_llama_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": "openlm-research/open_llama_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 "openlm-research/open_llama_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": "openlm-research/open_llama_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openlm-research/open_llama_13b with Docker Model Runner:
```
docker model run hf.co/openlm-research/open_llama_13b
```

question answering using llama

by Iamexperimenting - opened Jul 3, 2023

Discussion

Iamexperimenting

Jul 3, 2023

Hi,

Can someone tell me how to run question answering model using LLama? I'm trying to build QuestionAnswering model , when I run its not giving correct answer even though passing context along it.

from langchain import PromptTemplate, HugginFacePipeline, LLMChain
from transformers import pipeline
import torch
template  = """Read this article and answer the below question {context}\n {question} \n if you don;t know the answer please say "I don't know" don't make up on your own."""
prompt = PromptTemplate(template=template, input_variables=["context", "question"])
model_name = "openlm-research/llama-7b-hf"
hf_pipe = HugginFacePipeline(pipeline=pipeline(model=model_name, device='cuda:0', torch_dtype=torch.float16, max_new_tokens=512))
llm_chain = LLMChain(prompt=prompt, llm=hf_pipe)

torch.cuda.empty.cache()
result = llm_chain.run(context=input_context, question=user_question)

I'm using the above script but it is not giving correct answer even though answer present in the context, can someone help me here?

ttronrud

Jul 21, 2023

You're trying this with an untrained model, which is effectively a fancy auto-complete. The answer being present in the context doesn't matter if it doesn't know (e.g. its attention mechanism hasn't been trained) to look for it there!
Try fine-tuning the model first:
https://huggingface.co/docs/transformers/tasks/question_answering
https://colab.research.google.com/drive/1VoYNfYDKcKRQRor98Zbf2-9VQTtGJ24k?usp=sharing#scrollTo=XIyP_0r6zuVc

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment