Instructions to use saiful9379/Bangla_GPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saiful9379/Bangla_GPT2 with Transformers:

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

pipe = pipeline("text-generation", model="saiful9379/Bangla_GPT2")

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

tokenizer = AutoTokenizer.from_pretrained("saiful9379/Bangla_GPT2")
model = AutoModelForCausalLM.from_pretrained("saiful9379/Bangla_GPT2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use saiful9379/Bangla_GPT2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saiful9379/Bangla_GPT2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saiful9379/Bangla_GPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/saiful9379/Bangla_GPT2

SGLang

How to use saiful9379/Bangla_GPT2 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 "saiful9379/Bangla_GPT2" \
    --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": "saiful9379/Bangla_GPT2",
		"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 "saiful9379/Bangla_GPT2" \
        --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": "saiful9379/Bangla_GPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use saiful9379/Bangla_GPT2 with Docker Model Runner:
```
docker model run hf.co/saiful9379/Bangla_GPT2
```

saiful9379 commited on Mar 7, 2023

Commit

4a1210f

1 Parent(s): d851aa5

change config

Browse files

Files changed (1) hide show

config.json +10 -1

config.json CHANGED Viewed

@@ -26,5 +26,14 @@
   "summary_use_proj": true,
   "transformers_version": "4.22.1",
   "use_cache": true,
-  "vocab_size": 33391
 }

   "summary_use_proj": true,
   "transformers_version": "4.22.1",
   "use_cache": true,
+  "vocab_size": 33391,
+  "task_specific_params": {
+    "text-generation": {
+      max_length:175,
+      num_beams:10,
+      temperature: 0.7,
+      no_repeat_ngram_size : 2,
+      num_return_sequences:5
+    }
+  },
 }