Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,54 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Heralax/Augmentoolkit-DataSpecialist-v0.1
+tags:
+- axolotl
+- generated_from_trainer
+- mlx
+- mlx-my-repo
+datasets:
+- 29_mil_asstr.jsonl
+- 40mil_gutenberg.jsonl
+- hle-1_formatted_2mil.jsonl
+- 11_mil_fineweb.jsonl
+- multiturn_segments_shard_01.json
+- multiturn_segments_shard_02.json
+- singleturn_segments_shard_01.json
+- singleturn_segments_shard_02.json
+- openhermes2_5_shard_01.json
+- openhermes2_5_shard_02.json
+- openthoughts-1.parquet
+- openthoughts-2.parquet
+- qwq_10million.jsonl
+- bluemoon-6mil.json
+model-index:
+- name: datagen-sft-1
+  results: []
+---
+
+# LukasF/Augmentoolkit-DataSpecialist-v0.1-mlx-4Bit
+
+The Model [LukasF/Augmentoolkit-DataSpecialist-v0.1-mlx-4Bit](https://huggingface.co/LukasF/Augmentoolkit-DataSpecialist-v0.1-mlx-4Bit) was converted to MLX format from [Heralax/Augmentoolkit-DataSpecialist-v0.1](https://huggingface.co/Heralax/Augmentoolkit-DataSpecialist-v0.1) using mlx-lm version **0.22.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("LukasF/Augmentoolkit-DataSpecialist-v0.1-mlx-4Bit")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```