Instructions to use Hezam/ArabicT5-49GB-small-classification-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hezam/ArabicT5-49GB-small-classification-generation with Transformers:

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

pipe = pipeline("text-generation", model="Hezam/ArabicT5-49GB-small-classification-generation")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Hezam/ArabicT5-49GB-small-classification-generation")
model = AutoModelForSeq2SeqLM.from_pretrained("Hezam/ArabicT5-49GB-small-classification-generation", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Hezam/ArabicT5-49GB-small-classification-generation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hezam/ArabicT5-49GB-small-classification-generation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hezam/ArabicT5-49GB-small-classification-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hezam/ArabicT5-49GB-small-classification-generation

SGLang

How to use Hezam/ArabicT5-49GB-small-classification-generation 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 "Hezam/ArabicT5-49GB-small-classification-generation" \
    --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": "Hezam/ArabicT5-49GB-small-classification-generation",
		"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 "Hezam/ArabicT5-49GB-small-classification-generation" \
        --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": "Hezam/ArabicT5-49GB-small-classification-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hezam/ArabicT5-49GB-small-classification-generation with Docker Model Runner:
```
docker model run hf.co/Hezam/ArabicT5-49GB-small-classification-generation
```

Hezam commited on Dec 30, 2023

Commit

3c0a807

1 Parent(s): 94c274b

basic training

Browse files

Files changed (2) hide show

config.json +7 -6
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,8 +1,9 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/News/genreation_classifiction/model",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "d_ff": 2048,
   "d_kv": 64,
   "d_model": 512,
@@ -13,19 +14,19 @@
   "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 20,
   "num_heads": 8,
-  "num_layers": 20,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
   "use_cache": true,
-  "vocab_size": 32000
 }

 {
+  "_name_or_path": "/content/drive/MyDrive/news/model2",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
+  "classifier_dropout": 0.0,
   "d_ff": 2048,
   "d_kv": 64,
   "d_model": 512,
   "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
+  "num_decoder_layers": 16,
   "num_heads": 8,
+  "num_layers": 16,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
   "use_cache": true,
+  "vocab_size": 32128
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d8d902901621f0ab970625ec1d9d4f722fac6bfd3e117f66eda90cc8d3e635
-size 653096497

 version https://git-lfs.github.com/spec/v1
+oid sha256:06d6968e89d7cdf95af815e8dfb947c49865de30e830d504becbd207f20d4939
+size 735875429