Instructions to use goldfish-models/mar_deva_1000mb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use goldfish-models/mar_deva_1000mb with Transformers:

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

pipe = pipeline("text-generation", model="goldfish-models/mar_deva_1000mb")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("goldfish-models/mar_deva_1000mb")
model = AutoModelForCausalLM.from_pretrained("goldfish-models/mar_deva_1000mb")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use goldfish-models/mar_deva_1000mb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "goldfish-models/mar_deva_1000mb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "goldfish-models/mar_deva_1000mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/goldfish-models/mar_deva_1000mb

SGLang

How to use goldfish-models/mar_deva_1000mb 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 "goldfish-models/mar_deva_1000mb" \
    --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": "goldfish-models/mar_deva_1000mb",
		"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 "goldfish-models/mar_deva_1000mb" \
        --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": "goldfish-models/mar_deva_1000mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use goldfish-models/mar_deva_1000mb with Docker Model Runner:
```
docker model run hf.co/goldfish-models/mar_deva_1000mb
```

goldfish-models commited on Aug 26, 2024

Commit

a3fcc25

verified ·

1 Parent(s): 8b4e27f

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +3 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/1000mb/mar_deva_1000mb",
   "activation_function": "gelu",
   "architectures": [
     "GPT2LMHeadModel"
@@ -30,5 +30,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.18.0",
   "use_cache": true,
-  "vocab_size": 51200
 }

 {
+  "_name_or_path": "gpt_base_config.json",
   "activation_function": "gelu",
   "architectures": [
     "GPT2LMHeadModel"
   "torch_dtype": "float32",
   "transformers_version": "4.18.0",
   "use_cache": true,
+  "vocab_size": 51200,
+  "prefix": "[CLS]"
 }