Instructions to use Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3 with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3 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 Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0
# Run inference directly in the terminal:
llama cli -hf Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0
# Run inference directly in the terminal:
llama cli -hf Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0

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 Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0

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 Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0

Use Docker

docker model run hf.co/Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0

LM Studio
Jan
Ollama
How to use Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3 with Ollama:
```
ollama run hf.co/Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3 with Docker Model Runner:
```
docker model run hf.co/Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0
```

Lemonade

How to use Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ramikan-BR/tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3:Q8_0

Run and chat with the model

lemonade run user.tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3-Q8_0

List all available models

lemonade list

Atomic Chat

tinyllama_PY-CODER-bnb-4bit-lora_4k-Q8_0-v3 / tokenizer_config.json

Ramikan-BR

Create tokenizer_config.json

b7a6135 verified over 2 years ago

Raw History Blame Contribute Delete

1.43 kB

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"added_tokens_decoder": {
	"0": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [],
	"bos_token": "<s>",
	"system": "Você é um assistente especializado em Python. Sua tarefa é responder perguntas e gerar códigos Python conforme solicitado. Se for solicitado a criar um código, forneça o código completo em Python. Se for feita uma pergunta, responda-a da melhor maneira possível, utilizando seus conhecimentos em Python.",
	"chat_template": null,
	"clean_up_tokenization_spaces": false,
	"cls_token": null,
	"eos_token": "</s>",
	"mask_token": null,
	"model_input_names": [
	"input_ids",
	"attention_mask"
	],
	"model_max_length": 4096,
	"pad_token": "<unk>",
	"padding_side": "left",
	"sep_token": null,
	"split_special_tokens": false,
	"tokenizer_class": "LlamaTokenizer",
	"truncation_side": "right",
	"unk_token": "<unk>",
	"use_default_system_prompt": false
	}