Instructions to use Ramikan-BR/tinyllama-coder-py-4bit-v7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ramikan-BR/tinyllama-coder-py-4bit-v7 with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ramikan-BR/tinyllama-coder-py-4bit-v7", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ramikan-BR/tinyllama-coder-py-4bit-v7 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-coder-py-4bit-v7:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ramikan-BR/tinyllama-coder-py-4bit-v7: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 Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ramikan-BR/tinyllama-coder-py-4bit-v7: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 Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M

Use Docker

docker model run hf.co/Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M

LM Studio
Jan
Ollama
How to use Ramikan-BR/tinyllama-coder-py-4bit-v7 with Ollama:
```
ollama run hf.co/Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Ramikan-BR/tinyllama-coder-py-4bit-v7 with Docker Model Runner:
```
docker model run hf.co/Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M
```

Lemonade

How to use Ramikan-BR/tinyllama-coder-py-4bit-v7 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ramikan-BR/tinyllama-coder-py-4bit-v7:Q4_K_M

Run and chat with the model

lemonade run user.tinyllama-coder-py-4bit-v7-Q4_K_M

List all available models

lemonade list

Atomic Chat

tinyllama-coder-py-4bit-v7 / tokenizer_config.json

Ramikan-BR

Upload tokenizer

500fe96 verified over 2 years ago

Raw History Blame Contribute Delete

1.32 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
	}
	},
	"bos_token": "<s>",
	"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<\|user\|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<\|system\|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<\|assistant\|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<\|assistant\|>' }}\n{% endif %}\n{% endfor %}",
	"clean_up_tokenization_spaces": false,
	"eos_token": "</s>",
	"model_max_length": 4096,
	"pad_token": "<unk>",
	"padding_side": "left",
	"sp_model_kwargs": {},
	"tokenizer_class": "LlamaTokenizer",
	"unk_token": "<unk>",
	"use_default_system_prompt": false
	}