Safetensors
GGUF
Turkish
llama
Llama-3
instruct
finetune
chatml
gpt4
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
Instructions to use tda45/TdAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use tda45/TdAI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="tda45/TdAI", filename="llama.cpp/models/ggml-vocab-aquila.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use tda45/TdAI 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 tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
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 tda45/TdAI # Run inference directly in the terminal: ./llama-cli -hf tda45/TdAI
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 tda45/TdAI # Run inference directly in the terminal: ./build/bin/llama-cli -hf tda45/TdAI
Use Docker
docker model run hf.co/tda45/TdAI
- LM Studio
- Jan
- Ollama
How to use tda45/TdAI with Ollama:
ollama run hf.co/tda45/TdAI
- Unsloth Studio
How to use tda45/TdAI with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tda45/TdAI to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tda45/TdAI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tda45/TdAI to start chatting
- Atomic Chat new
- Docker Model Runner
How to use tda45/TdAI with Docker Model Runner:
docker model run hf.co/tda45/TdAI
- Lemonade
How to use tda45/TdAI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tda45/TdAI
Run and chat with the model
lemonade run user.TdAI-{{QUANT_TAG}}List all available models
lemonade list
| import { describe, it, expect } from 'vitest'; | |
| import { MessageRole } from '$lib/enums'; | |
| /** | |
| * Tests for the new reasoning content handling. | |
| * In the new architecture, reasoning content is stored in a dedicated | |
| * `reasoningContent` field on DatabaseMessage, not embedded in content with tags. | |
| * The API sends it as `reasoning_content` on ApiChatMessageData. | |
| */ | |
| describe('reasoning content in new structured format', () => { | |
| it('reasoning is stored as separate field, not in content', () => { | |
| // Simulate what the new chat store does | |
| const message = { | |
| content: 'The answer is 4.', | |
| reasoningContent: 'Let me think: 2+2=4, basic arithmetic.' | |
| }; | |
| // Content should be clean | |
| expect(message.content).not.toContain('<<<'); | |
| expect(message.content).toBe('The answer is 4.'); | |
| // Reasoning in dedicated field | |
| expect(message.reasoningContent).toBe('Let me think: 2+2=4, basic arithmetic.'); | |
| }); | |
| it('convertDbMessageToApiChatMessageData includes reasoning_content', () => { | |
| // Simulate the conversion logic | |
| const dbMessage = { | |
| role: MessageRole.ASSISTANT, | |
| content: 'The answer is 4.', | |
| reasoningContent: 'Let me think: 2+2=4, basic arithmetic.' | |
| }; | |
| const apiMessage: Record<string, unknown> = { | |
| role: dbMessage.role, | |
| content: dbMessage.content | |
| }; | |
| if (dbMessage.reasoningContent) { | |
| apiMessage.reasoning_content = dbMessage.reasoningContent; | |
| } | |
| expect(apiMessage.content).toBe('The answer is 4.'); | |
| expect(apiMessage.reasoning_content).toBe('Let me think: 2+2=4, basic arithmetic.'); | |
| // No internal tags leak into either field | |
| expect(apiMessage.content).not.toContain('<<<'); | |
| expect(apiMessage.reasoning_content).not.toContain('<<<'); | |
| }); | |
| it('API message excludes reasoning when excludeReasoningFromContext is true', () => { | |
| const dbMessage = { | |
| role: MessageRole.ASSISTANT, | |
| content: 'The answer is 4.', | |
| reasoningContent: 'internal thinking' | |
| }; | |
| const excludeReasoningFromContext = true; | |
| const apiMessage: Record<string, unknown> = { | |
| role: dbMessage.role, | |
| content: dbMessage.content | |
| }; | |
| if (!excludeReasoningFromContext && dbMessage.reasoningContent) { | |
| apiMessage.reasoning_content = dbMessage.reasoningContent; | |
| } | |
| expect(apiMessage.content).toBe('The answer is 4.'); | |
| expect(apiMessage.reasoning_content).toBeUndefined(); | |
| }); | |
| it('handles messages with no reasoning', () => { | |
| const dbMessage = { | |
| role: MessageRole.ASSISTANT, | |
| content: 'No reasoning here.', | |
| reasoningContent: undefined | |
| }; | |
| const apiMessage: Record<string, unknown> = { | |
| role: dbMessage.role, | |
| content: dbMessage.content | |
| }; | |
| if (dbMessage.reasoningContent) { | |
| apiMessage.reasoning_content = dbMessage.reasoningContent; | |
| } | |
| expect(apiMessage.content).toBe('No reasoning here.'); | |
| expect(apiMessage.reasoning_content).toBeUndefined(); | |
| }); | |
| }); | |