Instructions to use caikybaldo999/CBLM-Code-300M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caikybaldo999/CBLM-Code-300M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="caikybaldo999/CBLM-Code-300M-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("caikybaldo999/CBLM-Code-300M-Instruct")
model = AutoModelForCausalLM.from_pretrained("caikybaldo999/CBLM-Code-300M-Instruct", 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 caikybaldo999/CBLM-Code-300M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "caikybaldo999/CBLM-Code-300M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caikybaldo999/CBLM-Code-300M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/caikybaldo999/CBLM-Code-300M-Instruct

SGLang

How to use caikybaldo999/CBLM-Code-300M-Instruct 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 "caikybaldo999/CBLM-Code-300M-Instruct" \
    --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": "caikybaldo999/CBLM-Code-300M-Instruct",
		"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 "caikybaldo999/CBLM-Code-300M-Instruct" \
        --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": "caikybaldo999/CBLM-Code-300M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use caikybaldo999/CBLM-Code-300M-Instruct with Docker Model Runner:
```
docker model run hf.co/caikybaldo999/CBLM-Code-300M-Instruct
```

CBLM-Code-300M-Instruct

File size: 820 Bytes

ed204ef

---
library_name: transformers
pipeline_tag: text-generation
language:
- pt
- en
base_model: caikybaldo999/CBLM-Code-300M
tags:
- llama
- decoder-only
- instruct
- code
- portuguese
---

# CBLM Code 300M Instruct

Versão instruction-tuned de [caikybaldo999/CBLM-Code-300M](https://huggingface.co/caikybaldo999/CBLM-Code-300M).

- Arquitetura preservada do modelo-base: `LlamaForCausalLM`
- Parâmetros: `303,350,784`
- Contexto de SFT: `1024` tokens
- Treinamento completo dos pesos em BF16/FP16
- Dados de instrução em português e programação

## Formato de chat

Use `tokenizer.apply_chat_template(messages, add_generation_prompt=True)`.

## Limitações

Modelo experimental de aproximadamente 300M parâmetros. Pode errar fatos,
produzir código incorreto e gerar conteúdo inesperado. Verifique as respostas.