Instructions to use cminja/granitte-8b-code-instruct-sft-en-sr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cminja/granitte-8b-code-instruct-sft-en-sr with Transformers:

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

pipe = pipeline("text-generation", model="cminja/granitte-8b-code-instruct-sft-en-sr")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cminja/granitte-8b-code-instruct-sft-en-sr")
model = AutoModelForCausalLM.from_pretrained("cminja/granitte-8b-code-instruct-sft-en-sr")
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

vLLM

How to use cminja/granitte-8b-code-instruct-sft-en-sr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cminja/granitte-8b-code-instruct-sft-en-sr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cminja/granitte-8b-code-instruct-sft-en-sr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cminja/granitte-8b-code-instruct-sft-en-sr

SGLang

How to use cminja/granitte-8b-code-instruct-sft-en-sr 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 "cminja/granitte-8b-code-instruct-sft-en-sr" \
    --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": "cminja/granitte-8b-code-instruct-sft-en-sr",
		"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 "cminja/granitte-8b-code-instruct-sft-en-sr" \
        --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": "cminja/granitte-8b-code-instruct-sft-en-sr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cminja/granitte-8b-code-instruct-sft-en-sr with Docker Model Runner:
```
docker model run hf.co/cminja/granitte-8b-code-instruct-sft-en-sr
```

A full SFT of original 'ibm-granitte/granitte-8b-code-instruct' using a mix of English and Serbian instruction data.

Usage:

import torch from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # or "cpu" model_path = "cminja/granitte-8b-code-instruct" tokenizer = AutoTokenizer.from_pretrained(model_path)

drop device_map if running on CPU

model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) model.eval()

change input text as desired

chat = [ { "role": "user", "content": "Write a code to find the maximum value in a list of numbers." }, ] chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

tokenize the text

input_tokens = tokenizer(chat, return_tensors="pt")

transfer tokenized inputs to the device

for i in input_tokens: input_tokens[i] = input_tokens[i].to(device)

generate output tokens

output = model.generate(**input_tokens, max_new_tokens=100)

decode output tokens into text

output = tokenizer.batch_decode(output)

loop over the batch to print, in this example the batch size is 1

for i in output: print(i)

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16