Instructions to use rharris117/git-base-xr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rharris117/git-base-xr with Transformers:

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

pipe = pipeline("image-text-to-text", model="rharris117/git-base-xr")

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

tokenizer = AutoTokenizer.from_pretrained("rharris117/git-base-xr")
model = AutoModelForMultimodalLM.from_pretrained("rharris117/git-base-xr", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rharris117/git-base-xr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rharris117/git-base-xr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rharris117/git-base-xr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rharris117/git-base-xr

SGLang

How to use rharris117/git-base-xr 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 "rharris117/git-base-xr" \
    --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": "rharris117/git-base-xr",
		"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 "rharris117/git-base-xr" \
        --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": "rharris117/git-base-xr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rharris117/git-base-xr with Docker Model Runner:
```
docker model run hf.co/rharris117/git-base-xr
```

rharris117 commited on Jan 4, 2024

Commit

e82cb05

1 Parent(s): 9d88276

Training in progress, step 250

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Jan04_18-47-44_BobbyA100Train2/events.out.tfevents.1704394067.BobbyA100Train2.9782.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49232e06e92ffaed0ac66985c9c1de05a04c00c738928e1f3f9ae64721a033d6
 size 897269302

 version https://git-lfs.github.com/spec/v1
+oid sha256:fb90169859d1ff24b64562513bafcc78386badd3d3e7d5f86f3ff146143a4491
 size 897269302

runs/Jan04_18-47-44_BobbyA100Train2/events.out.tfevents.1704394067.BobbyA100Train2.9782.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5082e8eb83f7a450e65866f2359af21660235be33d686c18d2a2e1e5c3a4a23
-size 9851

 version https://git-lfs.github.com/spec/v1
+oid sha256:3a00b1c39d8d7e84e64ed2347d33f536b11b52e76690afbd15d832be2a627f7a
+size 10327