Instructions to use typeof/open_llama_3b_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use typeof/open_llama_3b_v2 with Transformers:

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

pipe = pipeline("text-generation", model="typeof/open_llama_3b_v2", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("typeof/open_llama_3b_v2")
model = AutoModelForCausalLM.from_pretrained("typeof/open_llama_3b_v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use typeof/open_llama_3b_v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "typeof/open_llama_3b_v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typeof/open_llama_3b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/typeof/open_llama_3b_v2

SGLang

How to use typeof/open_llama_3b_v2 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 "typeof/open_llama_3b_v2" \
    --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": "typeof/open_llama_3b_v2",
		"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 "typeof/open_llama_3b_v2" \
        --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": "typeof/open_llama_3b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use typeof/open_llama_3b_v2 with Docker Model Runner:
```
docker model run hf.co/typeof/open_llama_3b_v2
```

typeof commited on Oct 20, 2023

Commit

9c9a70e

1 Parent(s): d1ee5e7

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -8

README.md CHANGED Viewed

@@ -6,6 +6,10 @@ datasets:
 - togethercomputer/RedPajama-Data-1T
 ---
 # OpenLLaMA: An Open Reproduction of LLaMA
 **TL;DR**: we are releasing our public preview of OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA. We are releasing a series of 3B, 7B and 13B models trained on different data mixtures. Our model weights can serve as the drop in replacement of LLaMA in existing implementations.
@@ -24,14 +28,7 @@ Preview checkpoints can be directly loaded from Hugging Face Hub. **Please note
 import torch
 from transformers import LlamaTokenizer, LlamaForCausalLM
-## v2 models
-model_path = 'openlm-research/open_llama_3b_v2'
-# model_path = 'openlm-research/open_llama_7b_v2'
-## v1 models
-# model_path = 'openlm-research/open_llama_3b'
-# model_path = 'openlm-research/open_llama_7b'
-# model_path = 'openlm-research/open_llama_13b'
 tokenizer = LlamaTokenizer.from_pretrained(model_path)
 model = LlamaForCausalLM.from_pretrained(

 - togethercomputer/RedPajama-Data-1T
 ---
+# Tokenizer Fixed!! 🎉
+Thanks to https://huggingface.co/mistralai/Mistral-7B-v0.1/discussions/26/files
 # OpenLLaMA: An Open Reproduction of LLaMA
 **TL;DR**: we are releasing our public preview of OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA. We are releasing a series of 3B, 7B and 13B models trained on different data mixtures. Our model weights can serve as the drop in replacement of LLaMA in existing implementations.
 import torch
 from transformers import LlamaTokenizer, LlamaForCausalLM
+model_path = 'typeof/open_llama_3b_v2'
 tokenizer = LlamaTokenizer.from_pretrained(model_path)
 model = LlamaForCausalLM.from_pretrained(