Instructions to use Shresthadev403/bert-base-banking77-pt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shresthadev403/bert-base-banking77-pt2 with Transformers:

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

pipe = pipeline("text-generation", model="Shresthadev403/bert-base-banking77-pt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Shresthadev403/bert-base-banking77-pt2")
model = AutoModelForCausalLM.from_pretrained("Shresthadev403/bert-base-banking77-pt2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Shresthadev403/bert-base-banking77-pt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Shresthadev403/bert-base-banking77-pt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shresthadev403/bert-base-banking77-pt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Shresthadev403/bert-base-banking77-pt2

SGLang

How to use Shresthadev403/bert-base-banking77-pt2 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 "Shresthadev403/bert-base-banking77-pt2" \
    --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": "Shresthadev403/bert-base-banking77-pt2",
		"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 "Shresthadev403/bert-base-banking77-pt2" \
        --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": "Shresthadev403/bert-base-banking77-pt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Shresthadev403/bert-base-banking77-pt2 with Docker Model Runner:
```
docker model run hf.co/Shresthadev403/bert-base-banking77-pt2
```

Shresthadev403 commited on Dec 9, 2023

Commit

ca3baa8

1 Parent(s): 55e44ca

End of training

Browse files

Files changed (2) hide show

logs/events.out.tfevents.1702138817.62a1e4c74a80.28401.13 +3 -0
trainer_state.json +3 -3

logs/events.out.tfevents.1702138817.62a1e4c74a80.28401.13 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a51007bac99a29df63eee8e6c69138e45b6d32a54ae4f4887d56284eaa43c8e2
+size 4805

trainer_state.json CHANGED Viewed

@@ -55,9 +55,9 @@
       "step": 30,
       "total_flos": 1959690240000.0,
       "train_loss": 0.0,
-      "train_runtime": 0.241,
-      "train_samples_per_second": 124.469,
-      "train_steps_per_second": 124.469
     }
   ],
   "logging_steps": 10,

       "step": 30,
       "total_flos": 1959690240000.0,
       "train_loss": 0.0,
+      "train_runtime": 0.2088,
+      "train_samples_per_second": 143.66,
+      "train_steps_per_second": 143.66
     }
   ],
   "logging_steps": 10,