Create README.md

README.md

@@ -0,0 +1,98 @@
+# Merged-AGI-7B
+
+- Model creator: [KyujinHan](https://huggingface.co/kyujinpy)
+- Original model: [Merged AGI 7B](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
+
+## EXL2 Quants
+You can use [TheBloke's GPTQ quants](https://huggingface.co/TheBloke/Sakura-SOLAR-Instruct-GPTQ) for 4bit or lower. I'm providing higher exl2 quants so exllamav2 loader can still be used. Feel free to leave a suggestion for other quants.
+
+- [5.0bpw (main)](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/main)
+- [6.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/6.0bpw)
+- [7.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/7.0bpw)
+- [8.0bpw](https://huggingface.co/hgloow/MSakura-SOLAR-Instruct-EXL2/tree/8.0bpw)
+
+Zipped Quantization (if you want to download a single file)
+- [5.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/5.0bpw-zip)
+- [6.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/6.0bpw-zip)
+- [7.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/7.0bpw-zip)
+- [8.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/8.0bpw-zip)
+
+## Calibration Dataset
+Training dataset of Sakura-SOLAR-Instruct child models
+[argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo)
+
+## Memory Usage
+Use [TheBloke's 4bit-32g quants](https://huggingface.co/TheBloke/Sakura-SOLAR-Instruct-GPTQ/tree/gptq-4bit-32g-actorder_True) (7.4GB VRAM usage) if you have 8GB cards.
+
+Measured using ExLlamaV2 and 4096 max_seq_len with [Oobabooga's Text Generation WebUI](https://github.com/oobabooga/text-generation-webui/tree/main).
+| Branch | BPW | VRAM Usage | Description |
+| ------ | --- | ---------- | ----------- |
+[5.0bpw (main)](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/main)|5.0|7.7 GB|For >10GB VRAM cards
+[6.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/6.0bpw)|6.0|9.0 GB|For >=10GB VRAM cards with idle VRAM atleast or below 500MB (headroom for ui)
+[7.0bpw](https://huggingface.co/hgloow/Sakura-SOLAR-Instruct-EXL2/tree/7.0bpw)|7.0|10.2 GB|For >=11GB VRAM cards with idle VRAM atleast or below 500MB (headroom for ui)
+[8.0bpw](https://huggingface.co/hgloow/MSakura-SOLAR-Instruct-EXL2/tree/8.0bpw)|8.0|11.3 GB|For >=12GB VRAM cards with idle VRAM atleast or below 500MB (headroom for ui)
+
+## Prompt template: Orca-Hashes
+Courtesy of [TheBloke](https://huggingface.co/TheBloke)
+```
+### System:
+{system_message}
+
+### User:
+{prompt}
+
+### Assistant:
+
+```
+
+### If you use Oobabooga's Chat tab
+From my testing, the template "Orca-Mini" or any of the Orca templates produced the best result. Feel free to leave a suggestion if you know better.
+
+# Original Info
+# **Sakura-SOLAR-Instruct**  
+<img src='./sakura.png' width=512>
+  
+**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다**
+
+## Model Details
+
+**Model Developers** Kyujin Han (kyujinpy)
+
+**Method**  
+Using [Mergekit](https://github.com/cg123/mergekit).  
+I shared the information about my model. (training and code)  
+**Please see: [⭐Sakura-SOLAR](https://github.com/KyujinHan/Sakura-SOLAR-DPO).**  
+
+**Blog**
+- [Sakura-SOLAR 모델 제작 과정 및 후기](https://kyujinpy.tistory.com/122).   
+
+# **Model Benchmark**  
+
+## Open leaderboard
+- Follow up as [link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).  
+
+| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Sakura-SOLRCA-Instruct-DPO | 74.05 | 71.16 | 88.49 | 66.17 | 72.10 | 82.95 | 63.46 |
+| Sakura-SOLAR-Instruct-DPO-v2 | 74.14 | 70.90 | 88.41 | 66.48 | 71.86 | 83.43 | 63.76 |
+| [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct) | 74.40 | 70.99 | 88.42 | 66.33 | 71.79 | 83.66 | 65.20
+> Rank1 2023.12.27 PM 11:50
+
+   
+# Implementation Code
+```python
+### KO-Platypus
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+repo = "kyujinpy/Sakura-SOLAR-Instruct"
+OpenOrca = AutoModelForCausalLM.from_pretrained(
+        repo,
+        return_dict=True,
+        torch_dtype=torch.float16,
+        device_map='auto'
+)
+OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
+```
+
+---