Instructions to use vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa with Transformers:

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

pipe = pipeline("text-generation", model="vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa")
model = AutoModelForSeq2SeqLM.from_pretrained("vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa

SGLang

How to use vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa 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 "vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa" \
    --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": "vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa",
		"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 "vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa" \
        --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": "vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa with Docker Model Runner:
```
docker model run hf.co/vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa
```

asahi417 commited on Mar 26, 2023

Commit

bd9ac44

1 Parent(s): 2fc0771

Upload MT5ForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +1 -1
generation_config.json +1 -1
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -26,7 +26,7 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
   "use_cache": true,
   "vocab_size": 60002,
   "vocabtrimmer": {

   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
   "use_cache": true,
   "vocab_size": 60002,
   "vocabtrimmer": {

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.26.1"
 }

   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
+  "transformers_version": "4.27.2"
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07454e52b11cb29a5b6970c779f9b48367504e72cd9f91ae85971fb424be9e5d
 size 422081925

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1af285709fe51e6ba3a6695c80dc5ef9955ca04f6fd64d5d4716b3c800deeed
 size 422081925