Instructions to use MatLumber/Bisho with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MatLumber/Bisho with Transformers:

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

pipe = pipeline("text-generation", model="MatLumber/Bisho")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("MatLumber/Bisho")
model = AutoModelForMultimodalLM.from_pretrained("MatLumber/Bisho")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MatLumber/Bisho with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MatLumber/Bisho"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MatLumber/Bisho",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MatLumber/Bisho

SGLang

How to use MatLumber/Bisho 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 "MatLumber/Bisho" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MatLumber/Bisho",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MatLumber/Bisho" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MatLumber/Bisho",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MatLumber/Bisho with Docker Model Runner:
```
docker model run hf.co/MatLumber/Bisho
```

MatLumber commited on May 2, 2023

Commit

7f307b5

1 Parent(s): 0fc2b4f

Upload 10 files

Browse files

Files changed (3) hide show

eval_results.txt +1 -1
pytorch_model.bin +1 -1
training_args.bin +1 -1

eval_results.txt CHANGED Viewed

	@@ -1 +1 @@
1	- perplexity = tensor(1.~~5243~~)


1	+ perplexity = tensor(2.6852)

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142dcf76d97dc77f993dc86af5a0f17aac6e437e901db4bae6190bb441239f01
 size 510398013

 version https://git-lfs.github.com/spec/v1
+oid sha256:a03701ad194cb1333b81fcf8d63ce4331f90b2b73837fadd4533230b19be0964
 size 510398013

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6afa05e21f4092da7064719386bca54623aa11f600c3b96ac8abeb360b19d4
 size 1339

 version https://git-lfs.github.com/spec/v1
+oid sha256:7478f1c3c3d4ded422139a7c74f2763a703c393b7a8417499bf10a997064a61d
 size 1339