Instructions to use logicless/qwen25-coder-3b-sql-create-context-lora-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use logicless/qwen25-coder-3b-sql-create-context-lora-mlx 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("logicless/qwen25-coder-3b-sql-create-context-lora-mlx") 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 logicless/qwen25-coder-3b-sql-create-context-lora-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "logicless/qwen25-coder-3b-sql-create-context-lora-mlx" --prompt "Once upon a time"
- Atomic Chat
fix: make adapter config portable
Browse files- adapter_config.json +8 -40
adapter_config.json
CHANGED
|
@@ -1,41 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
"iters": 2500,
|
| 11 |
-
"learning_rate": 1e-05,
|
| 12 |
-
"lora_parameters": {
|
| 13 |
-
"rank": 16,
|
| 14 |
-
"dropout": 0.05,
|
| 15 |
-
"scale": 32.0
|
| 16 |
-
},
|
| 17 |
-
"lr_schedule": null,
|
| 18 |
-
"mask_prompt": true,
|
| 19 |
-
"max_seq_length": 2048,
|
| 20 |
-
"model": "mlx-community/Qwen2.5-Coder-3B-Instruct-4bit",
|
| 21 |
-
"num_layers": 16,
|
| 22 |
-
"optimizer": "adam",
|
| 23 |
-
"optimizer_config": {
|
| 24 |
-
"adam": {},
|
| 25 |
-
"adamw": {},
|
| 26 |
-
"muon": {},
|
| 27 |
-
"sgd": {},
|
| 28 |
-
"adafactor": {}
|
| 29 |
-
},
|
| 30 |
-
"project_name": null,
|
| 31 |
-
"report_to": null,
|
| 32 |
-
"resume_adapter_file": null,
|
| 33 |
-
"save_every": 100,
|
| 34 |
-
"seed": 20260914,
|
| 35 |
-
"steps_per_eval": 200,
|
| 36 |
-
"steps_per_report": 10,
|
| 37 |
-
"test": false,
|
| 38 |
-
"test_batches": 500,
|
| 39 |
-
"train": true,
|
| 40 |
-
"val_batches": 25
|
| 41 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"fine_tune_type": "lora",
|
| 3 |
+
"num_layers": 16,
|
| 4 |
+
"lora_parameters": {
|
| 5 |
+
"rank": 16,
|
| 6 |
+
"dropout": 0.05,
|
| 7 |
+
"scale": 32.0
|
| 8 |
+
}
|
| 9 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|