Instructions to use letsdatascience/qwen3.5-0.8b-spider-sql-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use letsdatascience/qwen3.5-0.8b-spider-sql-lora 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("letsdatascience/qwen3.5-0.8b-spider-sql-lora") 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 letsdatascience/qwen3.5-0.8b-spider-sql-lora with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "letsdatascience/qwen3.5-0.8b-spider-sql-lora" --prompt "Once upon a time"
- Atomic Chat
Qwen3.5-0.8B text-to-SQL LoRA adapter: distilled from DeepSeek V4 Flash, then GRPO (71.9% Spider dev, official rules)
168fd12 verified Download adapter_config.json from letsdatascience/qwen3.5-0.8b-spider-sql-lora: direct link, hf CLI and curl.
- Browser
- Download file 164 Bytes
-
https://huggingface.co/letsdatascience/qwen3.5-0.8b-spider-sql-lora/resolve/main/adapter_config.json
- Command line
-
hf download hf://letsdatascience/qwen3.5-0.8b-spider-sql-lora/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/letsdatascience/qwen3.5-0.8b-spider-sql-lora/resolve/main/adapter_config.json
164 Bytes
| { | |
| "model": "Qwen/Qwen3.5-0.8B", | |
| "fine_tune_type": "lora", | |
| "num_layers": -1, | |
| "lora_parameters": { | |
| "rank": 16, | |
| "dropout": 0.0, | |
| "scale": 2.0 | |
| } | |
| } | |