Text Generation
Transformers
TensorBoard
Safetensors
English
alicet5_moe
text2text-generation
pretrained
from-scratch
tiny-llm-ablation
custom_code
ul2
Mixture of Experts
encoder-decoder
Eval Results (legacy)
Instructions to use d0rj/t5-moe-55M-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use d0rj/t5-moe-55M-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="d0rj/t5-moe-55M-base", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("d0rj/t5-moe-55M-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use d0rj/t5-moe-55M-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "d0rj/t5-moe-55M-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "d0rj/t5-moe-55M-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/d0rj/t5-moe-55M-base
- SGLang
How to use d0rj/t5-moe-55M-base 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 "d0rj/t5-moe-55M-base" \ --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": "d0rj/t5-moe-55M-base", "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 "d0rj/t5-moe-55M-base" \ --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": "d0rj/t5-moe-55M-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use d0rj/t5-moe-55M-base with Docker Model Runner:
docker model run hf.co/d0rj/t5-moe-55M-base
Fix supported pipeline tag in model card
Browse files- README.md +1 -1
- release-manifest.json +1 -1
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
library_name: transformers
|
| 5 |
-
pipeline_tag:
|
| 6 |
tags:
|
| 7 |
- pretrained
|
| 8 |
- from-scratch
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
library_name: transformers
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
tags:
|
| 7 |
- pretrained
|
| 8 |
- from-scratch
|
release-manifest.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"repo": "d0rj/t5-moe-55M-base",
|
| 3 |
"files_sha256": {
|
| 4 |
-
"README.md": "
|
| 5 |
"config.json": "9c8269b3382032c7a33c52a6b1298533226a32df2b2f852af2b8a1833d188b9a",
|
| 6 |
"configuration_alicet5_moe.py": "b4015a6c1209a3fba371c7240df1755e697be99d53fc0c06066a55e02cda0e58",
|
| 7 |
"evaluation/adapters.py": "5a881b82bf6938ca953be751de021889f2c51a559df88f537da1e6ce4dfc6e15",
|
|
|
|
| 1 |
{
|
| 2 |
"repo": "d0rj/t5-moe-55M-base",
|
| 3 |
"files_sha256": {
|
| 4 |
+
"README.md": "4191b540f8d678a5259a507166a6a86c5570dfd1e346e12ed65151ceda376ef0",
|
| 5 |
"config.json": "9c8269b3382032c7a33c52a6b1298533226a32df2b2f852af2b8a1833d188b9a",
|
| 6 |
"configuration_alicet5_moe.py": "b4015a6c1209a3fba371c7240df1755e697be99d53fc0c06066a55e02cda0e58",
|
| 7 |
"evaluation/adapters.py": "5a881b82bf6938ca953be751de021889f2c51a559df88f537da1e6ce4dfc6e15",
|