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 { Zap, Globe, Radio } from '@lucide/svelte'; | |
| import { MCPTransportType } from '$lib/enums'; | |
| import type { ClientCapabilities, Implementation } from '$lib/types'; | |
| import type { Component } from 'svelte'; | |
| import { MimeTypeImage } from '$lib/enums/files.enums'; | |
| export const DEFAULT_CLIENT_VERSION = '1.0.0'; | |
| export const MCP_CLIENT_NAME = 'llama-ui-mcp'; | |
| export const DEFAULT_IMAGE_MIME_TYPE = MimeTypeImage.PNG; | |
| /** MIME types considered safe for rendering MCP server icons */ | |
| export const MCP_ALLOWED_ICON_MIME_TYPES = new Set([ | |
| MimeTypeImage.PNG, | |
| MimeTypeImage.JPEG, | |
| MimeTypeImage.JPG, | |
| MimeTypeImage.SVG, | |
| MimeTypeImage.WEBP, | |
| MimeTypeImage.ICO, | |
| MimeTypeImage.ICO_MICROSOFT | |
| ]); | |
| /** | |
| * MCP specification version this client targets. | |
| * Update when the upstream MCP spec introduces a new stable version: | |
| * https://spec.modelcontextprotocol.io/ | |
| */ | |
| export const MCP_PROTOCOL_VERSION = '2025-06-18'; | |
| export const DEFAULT_MCP_CONFIG = { | |
| protocolVersion: MCP_PROTOCOL_VERSION, | |
| capabilities: { tools: { listChanged: true } } as ClientCapabilities, | |
| clientInfo: { name: MCP_CLIENT_NAME, version: DEFAULT_CLIENT_VERSION } as Implementation, | |
| requestTimeoutSeconds: 300, // 5 minutes for long-running tools | |
| connectionTimeoutMs: 10_000 // 10 seconds for connection establishment | |
| } as const; | |
| export const MCP_SERVER_ID_PREFIX = 'LlamaUI-MCP-Server'; | |
| export const MCP_RECONNECT_INITIAL_DELAY = 1000; | |
| export const MCP_RECONNECT_BACKOFF_MULTIPLIER = 2; | |
| export const MCP_RECONNECT_MAX_DELAY = 30000; | |
| /** Per-attempt timeout for a single reconnection attempt before giving up and backing off. */ | |
| export const MCP_RECONNECT_ATTEMPT_TIMEOUT_MS = 15_000; | |
| /** Maximum number of MCP server avatars to display in the chat form */ | |
| export const MAX_DISPLAYED_MCP_AVATARS = 4; | |
| /** Expected count when two theme-less icons represent a light/dark pair */ | |
| export const EXPECTED_THEMED_ICON_PAIR_COUNT = 2; | |
| /** CORS proxy URL query parameter name */ | |
| export const CORS_PROXY_URL_PARAM = 'url'; | |
| /** Header prefix for headers that should be forwarded by the CORS proxy */ | |
| export const CORS_PROXY_HEADER_PREFIX = 'x-llama-server-proxy-header-'; | |
| /** Number of trailing characters to keep visible when partially redacting mcp-session-id */ | |
| export const MCP_SESSION_ID_VISIBLE_CHARS = 5; | |
| /** Partial-redaction rules for MCP headers: header name -> visible trailing chars */ | |
| export const MCP_PARTIAL_REDACT_HEADERS = new Map<string, number>([ | |
| ['mcp-session-id', MCP_SESSION_ID_VISIBLE_CHARS] | |
| ]); | |
| /** Header names whose values should be redacted in diagnostic logs */ | |
| export const REDACTED_HEADERS = new Set([ | |
| 'authorization', | |
| 'api-key', | |
| 'cookie', | |
| 'mcp-session-id', | |
| 'proxy-authorization', | |
| 'set-cookie', | |
| 'x-auth-token', | |
| 'x-api-key' | |
| ]); | |
| /** Human-readable labels for MCP transport types */ | |
| export const MCP_TRANSPORT_LABELS: Record<MCPTransportType, string> = { | |
| [MCPTransportType.WEBSOCKET]: 'WebSocket', | |
| [MCPTransportType.STREAMABLE_HTTP]: 'HTTP', | |
| [MCPTransportType.SSE]: 'SSE' | |
| }; | |
| /** Icon components for MCP transport types */ | |
| export const MCP_TRANSPORT_ICONS: Record<MCPTransportType, Component> = { | |
| [MCPTransportType.WEBSOCKET]: Zap, | |
| [MCPTransportType.STREAMABLE_HTTP]: Globe, | |
| [MCPTransportType.SSE]: Radio | |
| }; | |
| /** Standard SSE endpoint path indicators */ | |
| export const MCP_SSE_ENDPOINT = '/sse'; | |
| export const MCP_SSE_ENDPOINT_SLASH = '/sse/'; | |
| export const MCP_SSE_ENDPOINT_QUERY = '/sse?'; | |