Text Generation
Transformers
PyTorch
Southern Ndebele
English
m2m_100
text2text-generation
m2m100
translation
africanlp
african
ndebele
Instructions to use dsfsi/nr-en-m2m100-gov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dsfsi/nr-en-m2m100-gov with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dsfsi/nr-en-m2m100-gov")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("dsfsi/nr-en-m2m100-gov") model = AutoModelForSeq2SeqLM.from_pretrained("dsfsi/nr-en-m2m100-gov", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dsfsi/nr-en-m2m100-gov with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dsfsi/nr-en-m2m100-gov" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dsfsi/nr-en-m2m100-gov", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dsfsi/nr-en-m2m100-gov
- SGLang
How to use dsfsi/nr-en-m2m100-gov 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 "dsfsi/nr-en-m2m100-gov" \ --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": "dsfsi/nr-en-m2m100-gov", "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 "dsfsi/nr-en-m2m100-gov" \ --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": "dsfsi/nr-en-m2m100-gov", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dsfsi/nr-en-m2m100-gov with Docker Model Runner:
docker model run hf.co/dsfsi/nr-en-m2m100-gov
Upload 2 files
Browse files- .DS_Store +0 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +0 -0
- special_tokens_map.json +0 -0
- vocab.json +0 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu": 8.0464,
|
| 3 |
+
"predict_gen_len": 43.4231,
|
| 4 |
+
"predict_loss": 3.0210020542144775,
|
| 5 |
+
"predict_runtime": 307.9276,
|
| 6 |
+
"predict_samples": 702,
|
| 7 |
+
"predict_samples_per_second": 2.28,
|
| 8 |
+
"predict_steps_per_second": 0.572
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf8a5bf936280546d0ac5d903aee608fec19aaed1e98af968302df304b39c128
|
| 3 |
+
size 1944201353
|
sentencepiece.bpe.model
CHANGED
|
File without changes
|
special_tokens_map.json
CHANGED
|
File without changes
|
vocab.json
CHANGED
|
File without changes
|