Instructions to use youssefoud/Genz-70b-AWQ-split with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use youssefoud/Genz-70b-AWQ-split with Transformers:

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

pipe = pipeline("text-generation", model="youssefoud/Genz-70b-AWQ-split")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("youssefoud/Genz-70b-AWQ-split")
model = AutoModelForCausalLM.from_pretrained("youssefoud/Genz-70b-AWQ-split")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use youssefoud/Genz-70b-AWQ-split with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "youssefoud/Genz-70b-AWQ-split"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "youssefoud/Genz-70b-AWQ-split",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/youssefoud/Genz-70b-AWQ-split

SGLang

How to use youssefoud/Genz-70b-AWQ-split 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 "youssefoud/Genz-70b-AWQ-split" \
    --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": "youssefoud/Genz-70b-AWQ-split",
		"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 "youssefoud/Genz-70b-AWQ-split" \
        --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": "youssefoud/Genz-70b-AWQ-split",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use youssefoud/Genz-70b-AWQ-split with Docker Model Runner:
```
docker model run hf.co/youssefoud/Genz-70b-AWQ-split
```

youssefoud commited on Oct 4, 2023

Commit

58bde90

1 Parent(s): 617857d

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

.gitattributes +1 -0
model-00004-of-00004_part_aa +3 -0
model-00004-of-00004_part_zz_0.bin +3 -0
model-00004-of-00004_part_zz_1.bin +3 -0
model-00004-of-00004_part_zz_2.bin +3 -0

.gitattributes CHANGED Viewed

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 model-00001-of-00004_part_aa filter=lfs diff=lfs merge=lfs -text
 model-00002-of-00004_part_aa filter=lfs diff=lfs merge=lfs -text
 model-00003-of-00004_part_aa filter=lfs diff=lfs merge=lfs -text

 model-00001-of-00004_part_aa filter=lfs diff=lfs merge=lfs -text
 model-00002-of-00004_part_aa filter=lfs diff=lfs merge=lfs -text
 model-00003-of-00004_part_aa filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004_part_aa filter=lfs diff=lfs merge=lfs -text

model-00004-of-00004_part_aa ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:87854f5c3196d4a29bfbfb88ed9a6f5bced8144d6830c87818fb7585f29c3a57
+size 104857600

model-00004-of-00004_part_zz_0.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2e52a83d779264b02132fa00a19340988f743cdb23b269ed5be2623101913f3c
+size 2306867200

model-00004-of-00004_part_zz_1.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:441b849b144d69b492bf31f1958f304e502eece8ae73f547629b83ea134090be
+size 2306867200

model-00004-of-00004_part_zz_2.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08869d18bfe38ccb09156bf0b2251e2cc2cd51227723be57d7298d9aa87ffcc2
+size 2151699224