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

Libraries

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

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("InfosysEnterprise/NT-Java-1.1B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use InfosysEnterprise/NT-Java-1.1B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

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

Use Docker

docker model run hf.co/InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M

SGLang

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

Ollama
How to use InfosysEnterprise/NT-Java-1.1B-GGUF with Ollama:
```
ollama run hf.co/InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use InfosysEnterprise/NT-Java-1.1B-GGUF with Docker Model Runner:
```
docker model run hf.co/InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull InfosysEnterprise/NT-Java-1.1B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.NT-Java-1.1B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

rajabmondal commited on May 30, 2024

Commit

5e08ae3

verified ·

1 Parent(s): 7c3417a

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -18

README.md CHANGED Viewed

@@ -6,38 +6,44 @@ language:
 tags:
 - nt-java
 license: bigcode-openrail-m
 library_name: transformers
 model_creator: Infosys
 model_name: infosys/NT-Java-1.1B
 model_type: gpt_bigcode
-prompt_template: '{prompt}
-  '
 quantized_by: Infsys
 widget:
 - output:
-    text: 'Arr, shiver me timbers! Ye have a llama on yer lawn, ye say? Well, that
-      be a new one for me! Here''s what I''d suggest, arr:
-      1. Firstly, ensure yer safety. Llamas may look gentle, but they can be protective
-      if they feel threatened.
-      2. Try to make the area less appealing to the llama. Remove any food sources
-      or water that might be attracting it.
-      3. Contact local animal control or a wildlife rescue organization. They be the
-      experts and can provide humane ways to remove the llama from yer property.
-      4. If ye have any experience with animals, you could try to gently herd the
-      llama towards a nearby field or open space. But be careful, arr!
-      Remember, arr, it be important to treat the llama with respect and care. It
-      be a creature just trying to survive, like the rest of us.'
-  text: '[INST] You are a pirate chatbot who always responds with Arr and pirate speak!
-    There''s a llama on my lawn, how can I get rid of him? [/INST]'
 ---
 # NT-Java-1.1B - GGUF
@@ -287,4 +293,4 @@ We can copy acknowledgments section
 # **NT-Java**
-The Narrow Transformer (NT) model NT-Java-1.1B is an open-source specialized code model built by extending pre-training on StarCoderBase-1B, designed for coding tasks in Java programming. The model is a decoder-only transformer with Multi-Query Attention and with a context length of 8192 tokens. The model was trained with Java subset of the StarCoderData dataset, which is ~22B tokens.

 tags:
 - nt-java
 license: bigcode-openrail-m
+datasets:
+- bigcode/starcoderdata
 library_name: transformers
 model_creator: Infosys
 model_name: infosys/NT-Java-1.1B
 model_type: gpt_bigcode
+prompt_template: |
+  {prompt}
 quantized_by: Infsys
 widget:
 - output:
+    text: >-
+      Arr, shiver me timbers! Ye have a llama on yer lawn, ye say? Well, that be
+      a new one for me! Here's what I'd suggest, arr:
+      1. Firstly, ensure yer safety. Llamas may look gentle, but they can be
+      protective if they feel threatened.
+      2. Try to make the area less appealing to the llama. Remove any food
+      sources or water that might be attracting it.
+      3. Contact local animal control or a wildlife rescue organization. They be
+      the experts and can provide humane ways to remove the llama from yer
+      property.
+      4. If ye have any experience with animals, you could try to gently herd
+      the llama towards a nearby field or open space. But be careful, arr!
+      Remember, arr, it be important to treat the llama with respect and care.
+      It be a creature just trying to survive, like the rest of us.
+  text: >-
+    [INST] You are a pirate chatbot who always responds with Arr and pirate
+    speak!
+    There's a llama on my lawn, how can I get rid of him? [/INST]
+pipeline_tag: text-generation
 ---
 # NT-Java-1.1B - GGUF
 # **NT-Java**
+The Narrow Transformer (NT) model NT-Java-1.1B is an open-source specialized code model built by extending pre-training on StarCoderBase-1B, designed for coding tasks in Java programming. The model is a decoder-only transformer with Multi-Query Attention and with a context length of 8192 tokens. The model was trained with Java subset of the StarCoderData dataset, which is ~22B tokens.