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 { ParameterSyncService } from './parameter-sync.service'; | |
| import { ColorMode } from '$lib/enums'; | |
| describe('ParameterSyncService', () => { | |
| describe('roundFloatingPoint', () => { | |
| it('should fix JavaScript floating-point precision issues', () => { | |
| // Test the specific values from the screenshot | |
| const mockServerParams = { | |
| top_p: 0.949999988079071, | |
| min_p: 0.009999999776482582, | |
| temperature: 0.800000011920929, | |
| top_k: 40, | |
| samplers: ['top_k', 'typ_p', 'top_p', 'min_p', 'temperature'] | |
| }; | |
| const result = ParameterSyncService.extractServerDefaults({ | |
| ...mockServerParams, | |
| // Add other required fields to match the API type | |
| n_predict: 512, | |
| seed: -1, | |
| dynatemp_range: 0.0, | |
| dynatemp_exponent: 1.0, | |
| xtc_probability: 0.0, | |
| xtc_threshold: 0.1, | |
| typ_p: 1.0, | |
| repeat_last_n: 64, | |
| repeat_penalty: 1.0, | |
| presence_penalty: 0.0, | |
| frequency_penalty: 0.0, | |
| dry_multiplier: 0.0, | |
| dry_base: 1.75, | |
| dry_allowed_length: 2, | |
| dry_penalty_last_n: -1, | |
| mirostat: 0, | |
| mirostat_tau: 5.0, | |
| mirostat_eta: 0.1, | |
| stop: [], | |
| max_tokens: -1, | |
| n_keep: 0, | |
| n_discard: 0, | |
| ignore_eos: false, | |
| stream: true, | |
| logit_bias: [], | |
| n_probs: 0, | |
| min_keep: 0, | |
| grammar: '', | |
| grammar_lazy: false, | |
| grammar_triggers: [], | |
| preserved_tokens: [], | |
| chat_format: '', | |
| reasoning_format: '', | |
| reasoning_in_content: false, | |
| generation_prompt: '', | |
| 'speculative.n_max': 0, | |
| 'speculative.n_min': 0, | |
| 'speculative.p_min': 0.0, | |
| timings_per_token: false, | |
| post_sampling_probs: false, | |
| lora: [], | |
| top_n_sigma: 0.0, | |
| dry_sequence_breakers: [] | |
| } as ApiLlamaCppServerProps['default_generation_settings']['params']); | |
| // Check that the problematic floating-point values are rounded correctly | |
| expect(result.top_p).toBe(0.95); | |
| expect(result.min_p).toBe(0.01); | |
| expect(result.temperature).toBe(0.8); | |
| expect(result.top_k).toBe(40); // Integer should remain unchanged | |
| expect(result.samplers).toBe('top_k;typ_p;top_p;min_p;temperature'); | |
| }); | |
| it('should preserve non-numeric values', () => { | |
| const mockServerParams = { | |
| samplers: ['top_k', 'temperature'], | |
| max_tokens: -1, | |
| temperature: 0.7 | |
| }; | |
| const result = ParameterSyncService.extractServerDefaults({ | |
| ...mockServerParams, | |
| // Minimal required fields | |
| n_predict: 512, | |
| seed: -1, | |
| dynatemp_range: 0.0, | |
| dynatemp_exponent: 1.0, | |
| top_k: 40, | |
| top_p: 0.95, | |
| min_p: 0.05, | |
| xtc_probability: 0.0, | |
| xtc_threshold: 0.1, | |
| typ_p: 1.0, | |
| repeat_last_n: 64, | |
| repeat_penalty: 1.0, | |
| presence_penalty: 0.0, | |
| frequency_penalty: 0.0, | |
| dry_multiplier: 0.0, | |
| dry_base: 1.75, | |
| dry_allowed_length: 2, | |
| dry_penalty_last_n: -1, | |
| mirostat: 0, | |
| mirostat_tau: 5.0, | |
| mirostat_eta: 0.1, | |
| stop: [], | |
| n_keep: 0, | |
| n_discard: 0, | |
| ignore_eos: false, | |
| stream: true, | |
| logit_bias: [], | |
| n_probs: 0, | |
| min_keep: 0, | |
| grammar: '', | |
| grammar_lazy: false, | |
| grammar_triggers: [], | |
| preserved_tokens: [], | |
| chat_format: '', | |
| reasoning_format: '', | |
| reasoning_in_content: false, | |
| generation_prompt: '', | |
| 'speculative.n_max': 0, | |
| 'speculative.n_min': 0, | |
| 'speculative.p_min': 0.0, | |
| timings_per_token: false, | |
| post_sampling_probs: false, | |
| lora: [], | |
| top_n_sigma: 0.0, | |
| dry_sequence_breakers: [] | |
| } as ApiLlamaCppServerProps['default_generation_settings']['params']); | |
| expect(result.samplers).toBe('top_k;temperature'); | |
| expect(result.max_tokens).toBe(-1); | |
| expect(result.temperature).toBe(0.7); | |
| }); | |
| it('should merge ui settings from props when provided', () => { | |
| const result = ParameterSyncService.extractServerDefaults(null, { | |
| pasteLongTextToFileLen: 0, | |
| pdfAsImage: true, | |
| renderUserContentAsMarkdown: false, | |
| theme: ColorMode.DARK | |
| }); | |
| expect(result.pasteLongTextToFileLen).toBe(0); | |
| expect(result.pdfAsImage).toBe(true); | |
| expect(result.renderUserContentAsMarkdown).toBe(false); | |
| expect(result.theme).toBeUndefined(); | |
| }); | |
| }); | |
| }); | |