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
- Transformers
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
Create tokenizer_config.json
Browse files- tokenizer_config.json +51 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"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.",
|
| 33 |
+
"chat_template": null,
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"cls_token": null,
|
| 36 |
+
"eos_token": "</s>",
|
| 37 |
+
"mask_token": null,
|
| 38 |
+
"model_input_names": [
|
| 39 |
+
"input_ids",
|
| 40 |
+
"attention_mask"
|
| 41 |
+
],
|
| 42 |
+
"model_max_length": 4096,
|
| 43 |
+
"pad_token": "<unk>",
|
| 44 |
+
"padding_side": "left",
|
| 45 |
+
"sep_token": null,
|
| 46 |
+
"split_special_tokens": false,
|
| 47 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
+
"truncation_side": "right",
|
| 49 |
+
"unk_token": "<unk>",
|
| 50 |
+
"use_default_system_prompt": false
|
| 51 |
+
}
|