Text Generation
Safetensors
MLX
English
mlx-lm
prompt-reconstruction
prompt-inversion
prompt-recovery
inverse-prompting
response-to-prompt
semantic-similarity
ultrachat
qwen2.5
lora
apple-silicon
8-bit precision
quantized
small-language-model
Instructions to use ddrisco11/TROUT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use ddrisco11/TROUT with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("ddrisco11/TROUT") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use ddrisco11/TROUT with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "ddrisco11/TROUT" --prompt "Once upon a time"
- Atomic Chat
Download base-8bit/generation_config.json from ddrisco11/TROUT: direct link, hf CLI and curl.
- Browser
- Download file 242 Bytes
-
https://huggingface.co/ddrisco11/TROUT/resolve/main/base-8bit/generation_config.json
- Command line
-
hf download hf://ddrisco11/TROUT/base-8bit/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/ddrisco11/TROUT/resolve/main/base-8bit/generation_config.json
242 Bytes
| { | |
| "bos_token_id": 151643, | |
| "pad_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "repetition_penalty": 1.1, | |
| "temperature": 0.7, | |
| "top_p": 0.8, | |
| "top_k": 20, | |
| "transformers_version": "4.37.0" | |
| } | |