Instructions to use emozilla/open_llama_7b-scaled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emozilla/open_llama_7b-scaled with Transformers:

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

pipe = pipeline("text-generation", model="emozilla/open_llama_7b-scaled", trust_remote_code=True)

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

tokenizer = AutoTokenizer.from_pretrained("emozilla/open_llama_7b-scaled", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("emozilla/open_llama_7b-scaled", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use emozilla/open_llama_7b-scaled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emozilla/open_llama_7b-scaled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emozilla/open_llama_7b-scaled",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/emozilla/open_llama_7b-scaled

SGLang

How to use emozilla/open_llama_7b-scaled 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 "emozilla/open_llama_7b-scaled" \
    --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": "emozilla/open_llama_7b-scaled",
		"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 "emozilla/open_llama_7b-scaled" \
        --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": "emozilla/open_llama_7b-scaled",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use emozilla/open_llama_7b-scaled with Docker Model Runner:
```
docker model run hf.co/emozilla/open_llama_7b-scaled
```

emozilla commited on Jun 22, 2023

Commit

2d42031

1 Parent(s): b0d5977

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -7,9 +7,11 @@ datasets:
 This is a modified version of the original LLaMA model that incorporates Scaled Rotary Embeddings first proposed by [kaiokendev](https://kaiokendev.github.io/). By default, the model is configured to be equivalent to the original OpenLLaMA model (2048 context length). To modify, instantiate the LLaMA configuration and set `max_position_embeddings` to the desired context length. The value should be a power of 2, e.g. 2048, 4096, 8192, etc.
 ```python
-config = AutoConfig.from_pretrained("emozilla/open_llama_7b-scaled", trust_remote_code=True)
 config.max_position_embeddings = 8192
-model = AutoModelForCausalLM.from_pretrained("emozilla/open_llama_7b-scaled", config=config, trust_remote_code=True)
 ```
 You should also set `max_model_length` on your tokenizer.

 This is a modified version of the original LLaMA model that incorporates Scaled Rotary Embeddings first proposed by [kaiokendev](https://kaiokendev.github.io/). By default, the model is configured to be equivalent to the original OpenLLaMA model (2048 context length). To modify, instantiate the LLaMA configuration and set `max_position_embeddings` to the desired context length. The value should be a power of 2, e.g. 2048, 4096, 8192, etc.
 ```python
+config = AutoConfig.from_pretrained("emozilla/open_llama_7b-scaled", \
+  trust_remote_code=True)
 config.max_position_embeddings = 8192
+model = AutoModelForCausalLM.from_pretrained("emozilla/open_llama_7b-scaled", \
+  config=config, trust_remote_code=True)
 ```
 You should also set `max_model_length` on your tokenizer.