Instructions to use N8Programs/talkie-box with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use N8Programs/talkie-box with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("N8Programs/talkie-box") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use N8Programs/talkie-box with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "N8Programs/talkie-box"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "N8Programs/talkie-box" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "N8Programs/talkie-box", "messages": [ {"role": "user", "content": "Hello"} ] }'
Fix Talkie chat template leading newline
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"backend": "tokenizers",
|
| 3 |
-
"chat_template": "{%- set prelude = '
|
| 4 |
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"is_local": true,
|
|
|
|
| 1 |
{
|
| 2 |
"backend": "tokenizers",
|
| 3 |
+
"chat_template": "{%- set prelude = '\\nThe following conversation took place between the HUMAN, and TALKIE - a mechanical mind imbued with the knowledge of the world and the ability to use human language - a \"thinking machine\". It is published here for the benefit of the public:' -%}{{- prelude -}}{%- for message in messages -%}{%- if message['role'] == 'user' -%}{{- '\\n\\nHUMAN:\\n\\n' + (message['content'] | trim) -}}{%- elif message['role'] == 'assistant' -%}{{- '\\n\\nTALKIE:\\n\\n' + (message['content'] | trim) -}}{%- elif message['role'] == 'system' -%}{{- '\\n\\n' + (message['content'] | trim) -}}{%- else -%}{{- raise_exception('Unsupported role: ' + message['role']) -}}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt and (messages | length == 0 or messages[-1]['role'] != 'assistant') -%}{{- '\\n\\nTALKIE:\\n\\n' -}}{%- endif -%}",
|
| 4 |
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"is_local": true,
|