Instructions to use solidrust/Lorge-2x7B-UAMM-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Lorge-2x7B-UAMM-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Lorge-2x7B-UAMM-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Lorge-2x7B-UAMM-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Lorge-2x7B-UAMM-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use solidrust/Lorge-2x7B-UAMM-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Lorge-2x7B-UAMM-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/Lorge-2x7B-UAMM-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/solidrust/Lorge-2x7B-UAMM-AWQ

SGLang

How to use solidrust/Lorge-2x7B-UAMM-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 "solidrust/Lorge-2x7B-UAMM-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": "solidrust/Lorge-2x7B-UAMM-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 "solidrust/Lorge-2x7B-UAMM-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": "solidrust/Lorge-2x7B-UAMM-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use solidrust/Lorge-2x7B-UAMM-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Lorge-2x7B-UAMM-AWQ
```

Lorge-2x7B-UAMM-AWQ

Commit History

Updated base_model tag in README.md

f3aee51
verified

Suparious commited on Sep 3, 2024

Update README.md

d73e6a1
verified

Suparious commited on May 2, 2024

add default model card

a40caaf

first_name.last_name commited on Apr 30, 2024

adding quant config

f7b7232

first_name.last_name commited on Apr 30, 2024

adding AWQ model

a39f2dd

first_name.last_name commited on Apr 30, 2024

add processing notice

4d604f0

first_name.last_name commited on Apr 30, 2024

initial commit

2a8f9cb
verified

Suparious commited on Apr 30, 2024

Commit History

Updated base_model tag in README.md f3aee51 verified

Update README.md d73e6a1 verified

add default model card a40caaf

adding quant config f7b7232

adding AWQ model a39f2dd

add processing notice 4d604f0

initial commit 2a8f9cb verified

Updated base_model tag in README.md

f3aee51
verified

Update README.md

d73e6a1
verified

add default model card

a40caaf

adding quant config

f7b7232

adding AWQ model

a39f2dd

add processing notice

4d604f0

initial commit

2a8f9cb
verified