Edit model card

RP-7b-instruct

🚨 This model is tuning to RP and knowledge is likely unstable.

This is a merge of pre-trained language models created using mergekit.

Output example

[INST] <<SYS>>
あなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。また考える過程も出力してください。
<</SYS>>

まどマギで一番好きなキャラは? [/INST]まどマギで一番好きなキャラクターは、鹿目まどかです。彼女は物語の中心人物であり、優しくて芯の強い性格が魅力的です。また、彼女が魔法少女としての運命を受け入れ、他の魔法少女たちを救うために奔走する姿には感動します。彼女の最期の選択も、多くの人々の心に残る名シーンとなっています。

Test environment

This model was tested using text-generation-webui. I use preset min_p and Null preset with temperature=0.3 for Generation.

Usage

This format must be adhered to strictly, as deviations may result in less optimal outputs from the model.

The template used to construct a prompt for the Instruct model is specified as follows:

<s>[INST] <<SYS>>\n{SYSTEM_PROMPT}\n<</SYS>>\n\n{USER_MESSAGE_1} [/INST] {BOT_MESSAGE_1}</s>[INST] {USER_MESSAGE_2} [/INST] 

Please be aware that <s> and </s> are special tokens used for the beginning of string (BOS) and end of string (EOS), respectively, while [INST] and [/INST] are considered regular strings.

For the "{SYSTEM_PROMPT}" part, We recommend using "あなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。また考える過程も出力してください。"

For the "{USER_MESSAGE_1}" part, We recommend using {instruction}\n{input}

In other words, We recommend the following:

<s>[INST] <<SYS>>\nあなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。また考える過程も出力してください。\n<</SYS>>\n\n{instruction1}\n{input1} [/INST] {BOT_MESSAGE_1}</s>[INST] {instruction2}\n{input2} [/INST] 

Use the instruct model

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "nitky/RP-7b-instruct"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

device = "cuda"

messages = [
    {"role": "system", "content": "あなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。また考える過程も出力してください。"},
    {"role": "user", "content": "まどマギで一番好きなキャラは?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=256, do_sample=True, temperature=0.3)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Merge Details

Merge Method

This model was merged using the Model Stock merge method using stabilityai/japanese-stablelm-base-gamma-7b as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
base_model: stabilityai/japanese-stablelm-base-gamma-7b
models:
  - model: Aratako/AntlerStar-RP
  - model: Aratako/ArrowPro-7B-RobinHood-toxic
  - model: Aratako/Ninja-v1-RP-expressive
  - model: DataPilot/ArrowPro-7B-KUJIRA
  - model: DataPilot/ArrowPro-7B-RobinHood
  - model: DataPilot/ArrowPro-7B-KillerWhale
  - model: Elizezen/Phos-7B-RP
  - model: ohwi/japanese-stablelm-instruct-gamma-7b-dpo-uf-v1
  - model: umiyuki/Umievo-itr012-Gleipnir-7B
dtype: bfloat16
tokenizer_source: model:stabilityai/japanese-stablelm-base-gamma-7b
name: RP-7b-instruct
Downloads last month
24
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference API
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.

Merge of