Instructions to use bertin-project/bertin-gpt-j-6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bertin-project/bertin-gpt-j-6B with Transformers:

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

pipe = pipeline("text-generation", model="bertin-project/bertin-gpt-j-6B")

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

tokenizer = AutoTokenizer.from_pretrained("bertin-project/bertin-gpt-j-6B")
model = AutoModelForCausalLM.from_pretrained("bertin-project/bertin-gpt-j-6B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bertin-project/bertin-gpt-j-6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bertin-project/bertin-gpt-j-6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bertin-project/bertin-gpt-j-6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bertin-project/bertin-gpt-j-6B

SGLang

How to use bertin-project/bertin-gpt-j-6B 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 "bertin-project/bertin-gpt-j-6B" \
    --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": "bertin-project/bertin-gpt-j-6B",
		"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 "bertin-project/bertin-gpt-j-6B" \
        --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": "bertin-project/bertin-gpt-j-6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bertin-project/bertin-gpt-j-6B with Docker Model Runner:
```
docker model run hf.co/bertin-project/bertin-gpt-j-6B
```

versae commited on Jun 2, 2022

Commit

abafe00

1 Parent(s): d99da4a

Full precision weights, step 616001

Browse files

Files changed (2) hide show

config.json +2 -2
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -30,7 +30,7 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float16",
   "use_cache": true,
   "vocab_size": 50400
-}

       "max_length": 50
     }
   },
+  "torch_dtype": "float32",
   "use_cache": true,
   "vocab_size": 50400
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf7a88afd585692d2fbf75d0f5f96869a739e2d5f26cad62724247d79290773
-size 12106053103

 version https://git-lfs.github.com/spec/v1
+oid sha256:96797ab6196b309da3ccff4f49ac5072c9b9d0c8532274451e06eec446690351
+size 24207819307