Instructions to use InfosysEnterprise/NT-Java-1.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InfosysEnterprise/NT-Java-1.1B with Transformers:

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

pipe = pipeline("text-generation", model="InfosysEnterprise/NT-Java-1.1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("InfosysEnterprise/NT-Java-1.1B")
model = AutoModelForCausalLM.from_pretrained("InfosysEnterprise/NT-Java-1.1B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InfosysEnterprise/NT-Java-1.1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InfosysEnterprise/NT-Java-1.1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InfosysEnterprise/NT-Java-1.1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/InfosysEnterprise/NT-Java-1.1B

SGLang

How to use InfosysEnterprise/NT-Java-1.1B 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 "InfosysEnterprise/NT-Java-1.1B" \
    --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": "InfosysEnterprise/NT-Java-1.1B",
		"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 "InfosysEnterprise/NT-Java-1.1B" \
        --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": "InfosysEnterprise/NT-Java-1.1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use InfosysEnterprise/NT-Java-1.1B with Docker Model Runner:
```
docker model run hf.co/InfosysEnterprise/NT-Java-1.1B
```

rajabmondal commited on Jun 24, 2024

Commit

9057e2d

verified ·

1 Parent(s): 3baf79c

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -78,6 +78,8 @@ The model is intended for commercial use for Java programming tasks. The model p
 3. Code generation/Completion task in Java
 4. FIM task in Java
 ### Generation
 ```Java
 # pip install -q transformers
@@ -93,7 +95,17 @@ inputs = tokenizer.encode("public class HelloWorld {\n    public static void mai
 outputs = model.generate(inputs)
 print(tokenizer.decode(outputs[0]))
 ```
-#### Quantized Versions through `bitsandbytes`
 * _Using 8-bit precision (int8)_
 ```java

 3. Code generation/Completion task in Java
 4. FIM task in Java
+## Sample inference code
 ### Generation
 ```Java
 # pip install -q transformers
 outputs = model.generate(inputs)
 print(tokenizer.decode(outputs[0]))
 ```
+### Fill-in-the-middle
+Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:
+```Java
+input_text = "<fim_prefix>public class PalindromeChecker {\n        public static boolean isPalindrome(String str) {\n          <fim_suffix>return true;\n      }\n<fim_middle>"
+inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
+outputs = model.generate(inputs)
+print(tokenizer.decode(outputs[0]))
+```
+### Quantized Versions through `bitsandbytes`
 * _Using 8-bit precision (int8)_
 ```java