uploaded readme

README.md

@@ -0,0 +1,149 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+Llama3.1-ArrowSE-v0.4 - GGUF
+- Model creator: https://huggingface.co/DataPilot/
+- Original model: https://huggingface.co/DataPilot/Llama3.1-ArrowSE-v0.4/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [Llama3.1-ArrowSE-v0.4.Q2_K.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q2_K.gguf) | Q2_K | 2.96GB |
+| [Llama3.1-ArrowSE-v0.4.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
+| [Llama3.1-ArrowSE-v0.4.IQ3_S.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.IQ3_S.gguf) | IQ3_S | 3.43GB |
+| [Llama3.1-ArrowSE-v0.4.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
+| [Llama3.1-ArrowSE-v0.4.IQ3_M.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.IQ3_M.gguf) | IQ3_M | 3.52GB |
+| [Llama3.1-ArrowSE-v0.4.Q3_K.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q3_K.gguf) | Q3_K | 3.74GB |
+| [Llama3.1-ArrowSE-v0.4.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
+| [Llama3.1-ArrowSE-v0.4.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
+| [Llama3.1-ArrowSE-v0.4.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
+| [Llama3.1-ArrowSE-v0.4.Q4_0.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q4_0.gguf) | Q4_0 | 4.34GB |
+| [Llama3.1-ArrowSE-v0.4.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
+| [Llama3.1-ArrowSE-v0.4.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
+| [Llama3.1-ArrowSE-v0.4.Q4_K.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q4_K.gguf) | Q4_K | 4.58GB |
+| [Llama3.1-ArrowSE-v0.4.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
+| [Llama3.1-ArrowSE-v0.4.Q4_1.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q4_1.gguf) | Q4_1 | 4.78GB |
+| [Llama3.1-ArrowSE-v0.4.Q5_0.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q5_0.gguf) | Q5_0 | 5.21GB |
+| [Llama3.1-ArrowSE-v0.4.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
+| [Llama3.1-ArrowSE-v0.4.Q5_K.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q5_K.gguf) | Q5_K | 5.34GB |
+| [Llama3.1-ArrowSE-v0.4.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
+| [Llama3.1-ArrowSE-v0.4.Q5_1.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q5_1.gguf) | Q5_1 | 5.65GB |
+| [Llama3.1-ArrowSE-v0.4.Q6_K.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q6_K.gguf) | Q6_K | 6.14GB |
+| [Llama3.1-ArrowSE-v0.4.Q8_0.gguf](https://huggingface.co/RichardErkhov/DataPilot_-_Llama3.1-ArrowSE-v0.4-gguf/blob/main/Llama3.1-ArrowSE-v0.4.Q8_0.gguf) | Q8_0 | 7.95GB |
+
+
+
+
+Original model description:
+---
+base_model:
+- meta-llama/Meta-Llama-3.1-8B-Instruct
+- elyza/Llama-3-ELYZA-JP-8B
+- nvidia/Llama3-ChatQA-1.5-8B
+library_name: transformers
+tags:
+- mergekit
+- merge
+language:
+- ja
+license: llama3
+---
+
+## 概要　
+
+このモデルはllama3.1-8B-instructをもとに日本語性能を高めることを目的にMergekit&ファインチューニングを用いて作成されました。
+
+meta,ELYZA,nvidiaの皆様に感謝します。
+
+## how to use
+
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+DEFAULT_SYSTEM_PROMPT = "あなたは誠実で優秀な日本人のアシスタントです。特に指示が無い場合は、常に日本語で回答してください。"
+text = "Vtuberとして成功するために大切な5つのことを小学生にでもわかるように教えてください。"
+
+model_name = "DataPilot/Llama3.1-ArrowSE-v0.4"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto",
+)
+model.eval()
+
+messages = [
+    {"role": "system", "content": DEFAULT_SYSTEM_PROMPT},
+    {"role": "user", "content": text},
+]
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+token_ids = tokenizer.encode(
+    prompt, add_special_tokens=False, return_tensors="pt"
+)
+
+with torch.no_grad():
+    output_ids = model.generate(
+        token_ids.to(model.device),
+        max_new_tokens=1200,
+        do_sample=True,
+        temperature=0.6,
+        top_p=0.9,
+    )
+output = tokenizer.decode(
+    output_ids.tolist()[0][token_ids.size(1):], skip_special_tokens=True
+)
+print(output)
+```
+
+
+## merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using meta-llama/Meta-Llama-3.1-8B-Instruct as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
+* [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B)
+* [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: meta-llama/Meta-Llama-3.1-8B-Instruct
+    parameters:
+      weight: 1
+  - model: elyza/Llama-3-ELYZA-JP-8B
+    parameters:
+      weight: 0.7
+  - model: nvidia/Llama3-ChatQA-1.5-8B
+    parameters:
+      weight: 0.15
+merge_method: ties
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+parameters:
+  normalize: false
+dtype: bfloat16
+```
+