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, expect, it } from 'vitest'; | |
| import { parseHeadersToArray, serializeHeaders } from '$lib/utils/headers'; | |
| /** | |
| * Tests for the header serialization helpers used by the MCP server form | |
| * (custom header rows) and the new Authorization/Bearer-token flow. | |
| */ | |
| describe('parseHeadersToArray', () => { | |
| it('returns an empty array for empty or whitespace-only input', () => { | |
| expect(parseHeadersToArray('')).toEqual([]); | |
| expect(parseHeadersToArray(' ')).toEqual([]); | |
| expect(parseHeadersToArray(undefined as unknown as string)).toEqual([]); | |
| }); | |
| it('returns an empty array for invalid JSON input', () => { | |
| expect(parseHeadersToArray('{not-json')).toEqual([]); | |
| expect(parseHeadersToArray('[]')).toEqual([]); | |
| expect(parseHeadersToArray('"plain-string"')).toEqual([]); | |
| }); | |
| it('converts an object into ordered key/value pairs', () => { | |
| expect(parseHeadersToArray('{"X-Foo":"bar","Authorization":"Bearer abc"}')).toEqual([ | |
| { key: 'X-Foo', value: 'bar' }, | |
| { key: 'Authorization', value: 'Bearer abc' } | |
| ]); | |
| }); | |
| it('stringifies non-string values', () => { | |
| expect(parseHeadersToArray('{"count":"42","flag":"true"}')).toEqual([ | |
| { key: 'count', value: '42' }, | |
| { key: 'flag', value: 'true' } | |
| ]); | |
| }); | |
| }); | |
| describe('serializeHeaders', () => { | |
| it('returns an empty string when there are no valid pairs', () => { | |
| expect(serializeHeaders([])).toBe(''); | |
| expect(serializeHeaders([{ key: '', value: 'value' }])).toBe(''); | |
| expect(serializeHeaders([{ key: ' ', value: 'value' }])).toBe(''); | |
| }); | |
| it('returns an empty string when every pair has a blank key', () => { | |
| expect( | |
| serializeHeaders([ | |
| { key: '', value: 'drop-me' }, | |
| { key: ' ', value: 'drop-me-too' }, | |
| { key: '\t', value: 'tab-key' } | |
| ]) | |
| ).toBe(''); | |
| }); | |
| it('drops pairs with empty keys but keeps the rest', () => { | |
| expect( | |
| serializeHeaders([ | |
| { key: '', value: 'drop-me' }, | |
| { key: 'X-Keep', value: 'ok' } | |
| ]) | |
| ).toBe('{"X-Keep":"ok"}'); | |
| }); | |
| it('trims keys before serializing', () => { | |
| expect(serializeHeaders([{ key: ' X-Space ', value: 'ok' }])).toBe('{"X-Space":"ok"}'); | |
| }); | |
| it('preserves the input order of surviving pairs', () => { | |
| const serialized = serializeHeaders([ | |
| { key: 'X-C', value: '3' }, | |
| { key: 'X-A', value: '1' }, | |
| { key: 'X-B', value: '2' } | |
| ]); | |
| // Object key order follows insertion order in modern JS engines, so | |
| // the serialized JSON writes keys in our input order. | |
| expect(JSON.parse(serialized)).toEqual({ 'X-C': '3', 'X-A': '1', 'X-B': '2' }); | |
| }); | |
| }); | |
| describe('parseHeadersToArray / serializeHeaders roundtrip', () => { | |
| it('serializes back to an equal header object after a parse', () => { | |
| const original = JSON.stringify({ | |
| 'Content-Type': 'application/json', | |
| 'X-Trace-Id': 'abc-123' | |
| }); | |
| const roundtrip = serializeHeaders(parseHeadersToArray(original)); | |
| expect(JSON.parse(roundtrip)).toEqual(JSON.parse(original)); | |
| }); | |
| it('drops rows whose keys are blank after trimming during serialization', () => { | |
| const pairs = parseHeadersToArray('{"X-Keep":"ok","":"drop-me"}'); | |
| // parseHeadersToArray keeps raw key strings (the consumer is expected to | |
| // filter blanks, not the parser); serialization must strip them. | |
| expect(pairs).toEqual([ | |
| { key: 'X-Keep', value: 'ok' }, | |
| { key: '', value: 'drop-me' } | |
| ]); | |
| expect(serializeHeaders(pairs)).toBe('{"X-Keep":"ok"}'); | |
| }); | |
| it('preserves upstream keys untouched (does not lowercase them)', () => { | |
| const upperCased = '{"Authorization":"Bearer xyz"}'; | |
| const parsed = parseHeadersToArray(upperCased); | |
| expect(parsed).toEqual([{ key: 'Authorization', value: 'Bearer xyz' }]); | |
| }); | |
| it('bearer-token write survives a re-parse when paired with regular custom headers', () => { | |
| // The McpServerForm bearer UI writes {Authorization: `Bearer <token>`} | |
| // into the same headers string as the custom KV section. The round | |
| // trip below mirrors the exact shape the form produces so a future | |
| // refactor of either code path cannot silently change the on-disk key. | |
| const pairs = [ | |
| { key: 'X-Trace-Id', value: 'abc-123' }, | |
| { key: 'Authorization', value: 'Bearer super-secret' } | |
| ]; | |
| const serialized = serializeHeaders(pairs); | |
| expect(serialized).toBe('{"X-Trace-Id":"abc-123","Authorization":"Bearer super-secret"}'); | |
| expect(parseHeadersToArray(serialized)).toEqual(pairs); | |
| }); | |
| }); | |