nitky / Oumuamua-7b-instruct

huggingface.co
Total runs: 5
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: June 01 2024
text-generation

Introduction of Oumuamua-7b-instruct

Model Details of Oumuamua-7b-instruct

Oumuamua-7b-instruct

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>>

道路で泣いている子供がいます。その子供には何があったと考えられますか? [/INST] 道路で泣いている子供がいる場合、考えられる理由はいくつかあります。

1. 怪我をした: 転んで怪我をしたり、何かにぶつかって痛みを感じている可能性があります。
2. 迷子になった: 親や保護者とはぐれてしまった、または道に迷って不安になっている可能性があります。
3. お腹が空いた: 長時間食事をしていない、またはお腹が空いているために泣いている可能性があります。
4. 疲れた: 長時間歩いていたり、遊び疲れて疲れている可能性があります。
5. 寂しかった: 一人でいることに寂しさを感じている、または親や友達がいなくて寂しいと感じている可能性があります。
6. 怖い思いをした: 車や不審者に遭遇した、または何かに驚いた可能性があります。
7. 体調が悪い: 発熱や頭痛、吐き気などの体調不良を感じている可能性があります。
8. トイレに行きたい: おむつが濡れていたり、トイレに行きたくて泣いている可能性があります。
9. 何かを求めている: 注意を引きたかったり、助けを求めている可能性があります。

子供の状況をよく観察し、声をかけて話を聞いてみることが大切です。必要に応じて、保護者や警察、救急車を呼ぶなどの対応をする必要があるかもしれません。
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/Oumuamua-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": "道路で泣いている子供がいます。その子供には何があったと考えられますか?"}
]

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 nitky/Oumuamua-7b-base 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: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-v0.1-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: stabilityai/japanese-stablelm-base-gamma-7b
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: DataPilot/ArrowPro-7B-KillerWhale
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: ArrowPro-7B-KillerWhale-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: nitky/RP-7b-instruct
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: RP-7b-instruct-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-Instruct-v0.3
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: tokyotech-llm/Swallow-MS-7b-instruct-v0.1
    parameters:
      weight: 0.8
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight: -0.8
  - model: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: Mistral-7B-v0.1-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-alpha
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: ArrowPro-7B-KillerWhale-VE-Swallow-MS # include Mistral-7B-Instruct-v0.3
    parameters:
      weight: 0.8
  - model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-beta
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: RP-7b-instruct-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
    parameters:
      weight: -0.8
  - model: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: Mistral-7B-v0.1-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-gamma
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: Oumuamua-7b-instruct-alpha
  - model: Oumuamua-7b-instruct-beta
  - model: Oumuamua-7b-instruct-gamma
dtype: bfloat16
name: Oumuamua-7b-instruct

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

5
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

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

More Oumuamua-7b-instruct license Visit here:

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

Oumuamua-7b-instruct huggingface.co

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

Oumuamua-7b-instruct huggingface.co Url

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

nitky Oumuamua-7b-instruct online free

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

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

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

Oumuamua-7b-instruct install

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

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

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

Url of Oumuamua-7b-instruct

Oumuamua-7b-instruct huggingface.co Url

Provider of Oumuamua-7b-instruct huggingface.co

nitky
ORGANIZATIONS

Other API from nitky