Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use baban/MT_En_Hindi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use baban/MT_En_Hindi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="baban/MT_En_Hindi") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("baban/MT_En_Hindi") model = AutoModelForCausalLM.from_pretrained("baban/MT_En_Hindi", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use baban/MT_En_Hindi with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "baban/MT_En_Hindi" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baban/MT_En_Hindi", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/baban/MT_En_Hindi
- SGLang
How to use baban/MT_En_Hindi 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 "baban/MT_En_Hindi" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baban/MT_En_Hindi", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "baban/MT_En_Hindi" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baban/MT_En_Hindi", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use baban/MT_En_Hindi with Docker Model Runner:
docker model run hf.co/baban/MT_En_Hindi
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,39 @@ model-index:
|
|
| 10 |
- name: MT_En_Hindi
|
| 11 |
results: []
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
| 10 |
- name: MT_En_Hindi
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
+
```
|
| 14 |
+
import torch
|
| 15 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 16 |
+
|
| 17 |
+
# Load tokenizer and model
|
| 18 |
+
model_name = "baban/MT_En_Hindi"
|
| 19 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 20 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
|
| 21 |
+
|
| 22 |
+
source_text = "The weather is nice today."
|
| 23 |
+
prompt = f"Translate the following English sentence to Hindi:\n{source_text}"
|
| 24 |
+
|
| 25 |
+
messages = [
|
| 26 |
+
{"role": "user", "content": prompt}
|
| 27 |
+
]
|
| 28 |
+
|
| 29 |
+
# Tokenize the formatted input
|
| 30 |
+
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
with torch.no_grad():
|
| 34 |
+
output_ids = model.generate(
|
| 35 |
+
input_ids=input_ids,
|
| 36 |
+
max_new_tokens=100,
|
| 37 |
+
do_sample=False
|
| 38 |
+
)
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
# Decode and print only the new tokens (the response)
|
| 42 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[-1]:], skip_special_tokens=True)
|
| 43 |
+
print("\n=== Translation ===")
|
| 44 |
+
print(response)
|
| 45 |
+
```
|
| 46 |
|
| 47 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 48 |
should probably proofread and complete it, then remove this comment. -->
|