nitky / RP-7b-instruct

huggingface.co
Total runs: 6
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: June 01 2024
text-generation

Introduction of RP-7b-instruct

Model Details of RP-7b-instruct

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

Runs of nitky RP-7b-instruct on huggingface.co

6
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About RP-7b-instruct huggingface.co Model

More RP-7b-instruct license Visit here:

https://choosealicense.com/licenses/apache-2.0

RP-7b-instruct huggingface.co

RP-7b-instruct huggingface.co is an AI model on huggingface.co that provides RP-7b-instruct's model effect (), which can be used instantly with this nitky RP-7b-instruct model. huggingface.co supports a free trial of the RP-7b-instruct model, and also provides paid use of the RP-7b-instruct. Support call RP-7b-instruct model through api, including Node.js, Python, http.

RP-7b-instruct huggingface.co Url

https://huggingface.co/nitky/RP-7b-instruct

nitky RP-7b-instruct online free

RP-7b-instruct huggingface.co is an online trial and call api platform, which integrates RP-7b-instruct's modeling effects, including api services, and provides a free online trial of RP-7b-instruct, you can try RP-7b-instruct online for free by clicking the link below.

nitky RP-7b-instruct online free url in huggingface.co:

https://huggingface.co/nitky/RP-7b-instruct

RP-7b-instruct install

RP-7b-instruct is an open source model from GitHub that offers a free installation service, and any user can find RP-7b-instruct on GitHub to install. At the same time, huggingface.co provides the effect of RP-7b-instruct install, users can directly use RP-7b-instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

RP-7b-instruct install url in huggingface.co:

https://huggingface.co/nitky/RP-7b-instruct

Url of RP-7b-instruct

RP-7b-instruct huggingface.co Url

Provider of RP-7b-instruct huggingface.co

nitky
ORGANIZATIONS

Other API from nitky