Instructions to use mllm-dev/bill_sum_experiment_3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mllm-dev/bill_sum_experiment_3 with Transformers:

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

pipe = pipeline("text-generation", model="mllm-dev/bill_sum_experiment_3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mllm-dev/bill_sum_experiment_3")
model = AutoModelForCausalLM.from_pretrained("mllm-dev/bill_sum_experiment_3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mllm-dev/bill_sum_experiment_3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mllm-dev/bill_sum_experiment_3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mllm-dev/bill_sum_experiment_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mllm-dev/bill_sum_experiment_3

SGLang

How to use mllm-dev/bill_sum_experiment_3 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 "mllm-dev/bill_sum_experiment_3" \
    --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": "mllm-dev/bill_sum_experiment_3",
		"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 "mllm-dev/bill_sum_experiment_3" \
        --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": "mllm-dev/bill_sum_experiment_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mllm-dev/bill_sum_experiment_3 with Docker Model Runner:
```
docker model run hf.co/mllm-dev/bill_sum_experiment_3
```

mllm-dev commited on Mar 30, 2024

Commit

a072d81

verified ·

1 Parent(s): 330bf0c

Training in progress, epoch 3

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Mar30_00-21-12_lambda-hyperplane04/events.out.tfevents.1711783276.lambda-hyperplane04.1467686.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16117c1a7639b3a1cba01034fad6d675142a176425b34cdc857cca17436d3739
 size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:e1842c9ac0b7c34cbbc50409dc1b3faff10b9eac706c5e58922fa7869aba1505
 size 497774208

runs/Mar30_00-21-12_lambda-hyperplane04/events.out.tfevents.1711783276.lambda-hyperplane04.1467686.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e939f00c47b30e3a99ff16fb3b2e04a477190814868555b7a3784ccf86e593e
-size 5600

 version https://git-lfs.github.com/spec/v1
+oid sha256:7c741d32fc638df26e9edee79c6410e3e43c9266ec9095c55c4b0f02a1ef8d1e
+size 6861