Instructions to use Michielo/mt5-small_en-nl_translation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Michielo/mt5-small_en-nl_translation with Transformers:

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

pipe = pipeline("text-generation", model="Michielo/mt5-small_en-nl_translation")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Michielo/mt5-small_en-nl_translation")
model = AutoModelForSeq2SeqLM.from_pretrained("Michielo/mt5-small_en-nl_translation", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Michielo/mt5-small_en-nl_translation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Michielo/mt5-small_en-nl_translation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Michielo/mt5-small_en-nl_translation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Michielo/mt5-small_en-nl_translation

SGLang

How to use Michielo/mt5-small_en-nl_translation 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 "Michielo/mt5-small_en-nl_translation" \
    --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": "Michielo/mt5-small_en-nl_translation",
		"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 "Michielo/mt5-small_en-nl_translation" \
        --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": "Michielo/mt5-small_en-nl_translation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Michielo/mt5-small_en-nl_translation with Docker Model Runner:
```
docker model run hf.co/Michielo/mt5-small_en-nl_translation
```

Michielo commited on Apr 19, 2024

Commit

5f44cfb

verified ·

1 Parent(s): ff4f8f2

Improved model output quality

Browse files

Files changed (5) hide show

config.json +2 -2
generation_config.json +1 -1
model.safetensors +1 -1
tokenizer.json +2 -2
tokenizer_config.json +4 -0

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/mt5-small",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],
@@ -27,7 +27,7 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 250112
 }

 {
+  "_name_or_path": "output/checkpointt",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
   "use_cache": true,
   "vocab_size": 250112
 }

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "eos_token_id": 1,
   "max_length": 1024,
   "pad_token_id": 0,
-  "transformers_version": "4.37.2"
 }

   "eos_token_id": 1,
   "max_length": 1024,
   "pad_token_id": 0,
+  "transformers_version": "4.39.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edd7c27d32aba69c652ea06e49cd104526b02e2d4460a9bf7d27b3280b4d29f
 size 1200729512

 version https://git-lfs.github.com/spec/v1
+oid sha256:a6e8f097617c6f3379785eb4edbd501d52d2c4c876c142c7f85c114fa489309e
 size 1200729512

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722bf80470f2ae6a7cfeaaaf876fb7ef9ad33b2e9a514ded463498f4a8bbd6be
-size 16330661

 version https://git-lfs.github.com/spec/v1
+oid sha256:bb8aa17e32492b66346653b8954cf4c01f46717f63fd0c44b4c2d9fa36276392
+size 16315413

tokenizer_config.json CHANGED Viewed

@@ -30,9 +30,13 @@
   "eos_token": "</s>",
   "extra_ids": 0,
   "legacy": true,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

   "eos_token": "</s>",
   "extra_ids": 0,
   "legacy": true,
+  "max_length": 1024,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }