Instructions to use abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq with Transformers:

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

pipe = pipeline("text-generation", model="abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq")
model = AutoModelForMultimodalLM.from_pretrained("abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq

SGLang

How to use abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq 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 "abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq" \
    --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": "abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq",
		"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 "abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq" \
        --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": "abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq with Docker Model Runner:
```
docker model run hf.co/abhinavkulkarni/VMware-open-llama-7b-open-instruct-w4-g128-awq
```

abhinavkulkarni commited on Jul 9, 2023

Commit

c59e771

1 Parent(s): d2be62b

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ July 5, 2023
 ## Model License
-Please refer to the original model license ([link](https://huggingface.co/VMware/open-llama-7b-open-instruct)).
 Please refer to the AWQ quantization license ([link](https://github.com/llm-awq/blob/main/LICENSE)).
@@ -26,6 +26,8 @@ Please refer to the AWQ quantization license ([link](https://github.com/llm-awq/
 This model was successfully tested on CUDA driver v530.30.02 and runtime v11.7 with Python v3.10.11. Please note that AWQ requires NVIDIA GPUs with compute capability of 80 or higher.
 ## How to Use
 ```bash
@@ -62,7 +64,7 @@ q_config = {
 load_quant = hf_hub_download('abhinavkulkarni/open-llama-7b-open-instruct-w4-g128-awq', 'pytorch_model.bin')
 with init_empty_weights():
-    model = AutoModelForCausalLM.from_pretrained(model_name, config=config,
                                                  torch_dtype=torch.float16, trust_remote_code=True)
 real_quantize_model_weight(model, w_bit=w_bit, q_config=q_config, init_only=True)

 ## Model License
+Please refer to original MPT model license ([link](https://huggingface.co/VMware/open-llama-7b-open-instruct)).
 Please refer to the AWQ quantization license ([link](https://github.com/llm-awq/blob/main/LICENSE)).
 This model was successfully tested on CUDA driver v530.30.02 and runtime v11.7 with Python v3.10.11. Please note that AWQ requires NVIDIA GPUs with compute capability of 80 or higher.
+For Docker users, the `nvcr.io/nvidia/pytorch:23.06-py3` image is runtime v12.1 but otherwise the same as the configuration above and has also been verified to work.
 ## How to Use
 ```bash
 load_quant = hf_hub_download('abhinavkulkarni/open-llama-7b-open-instruct-w4-g128-awq', 'pytorch_model.bin')
 with init_empty_weights():
+    model = AutoModelForCausalLM.from_config(config=config,
                                                  torch_dtype=torch.float16, trust_remote_code=True)
 real_quantize_model_weight(model, w_bit=w_bit, q_config=q_config, init_only=True)