Oumuamua-7b-instruct-v2-GGUF

This is quantized version of nitky/Oumuamua-7b-instruct-v2 created using llama.cpp

Model Description

๐Ÿšจ If you want to avoid outputs that appear to be literal translations, please prompt this model to role-play as a Japanese person.

image/png

  • Understanding user intent in messages
  • Providing helpful and harmless responses
  • Enhancing expertise in human and computer-related topics
  • Improving role-playing capabilities
  • Enhancing performance in multi-turn conversations

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

Output example

  • temparture: 0.1
  • top_p: 1.0
[INST]<<SYS>>
ใ‚ใชใŸใฏ่ช ๅฎŸใงๅ„ช็ง€ใชๆ—ฅๆœฌไบบใฎใ‚ขใ‚ทใ‚นใ‚ฟใƒณใƒˆใงใ™ใ€‚ 
<</SYS>>

ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ข๏ผˆOumuamua๏ผ‰ใฏใ€2017ๅนดใซ็™บ่ฆ‹ใ•ใ‚ŒใŸใ€ๅคฉไฝ“่ฆณๆธฌๅฒไธŠๅˆใ‚ใฆๅคช้™ฝ็ณปๅค–ใ‹ใ‚‰้ฃ›ๆฅใ—ใŸๆ’ๆ˜Ÿ้–“ๅคฉไฝ“ใงใ™ใ€‚ใ“ใ‚Œใ‚’ใƒ†ใƒผใƒžใซใ—ใŸๅฐ่ชฌใฎ่จญๅฎšใ‚’่€ƒใˆใฆใใ ใ•ใ„ใ€‚ [/INST] ใ‚ฟใ‚คใƒˆใƒซ:ใ€Œใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ้บ็”ฃใ€

ใ‚ใ‚‰ใ™ใ˜:
2017ๅนดใ€ๅคฉไฝ“่ฆณๆธฌๅฒไธŠๅˆใฎๅคช้™ฝ็ณปๅค–ใ‹ใ‚‰ใฎ้ฃ›ๆฅ็‰ฉไฝ“ใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใŒ็™บ่ฆ‹ใ•ใ‚ŒใŸใ€‚ใ“ใฎๅคฉไฝ“ใฏใ€่ฌŽใซๅŒ…ใพใ‚ŒใŸ่ตทๆบใจ็›ฎ็š„ใ‚’ๆŒใคใ“ใจใ‹ใ‚‰ใ€ไธ–็•Œไธญใฎ็ง‘ๅญฆ่€…ใ‚„็ ”็ฉถ่€…ใŒใใฎ่งฃๆ˜Žใซ็†ฑใ‚’ๅ…ฅใ‚ŒใŸใ€‚ไธปไบบๅ…ฌใฏใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ็ ”็ฉถใซๆƒ…็†ฑใ‚’ๆณจใ่‹ฅใๅคฉๆ–‡ๅญฆ่€…ใ€ใƒŸใ‚ญใƒปใ‚ตใƒˆใ‚ฆใ€‚ๅฝผใฏใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใŒ็™บใ™ใ‚‹ๅฅ‡ๅฆ™ใชไฟกๅทใ‚’ๅถ็„ถใซใ‚‚่งฃ่ชญใ—ใ€ใใ‚ŒใŒ้ซ˜ๅบฆใชๆ–‡ๆ˜Žใซใ‚ˆใฃใฆไฝœใ‚‰ใ‚ŒใŸใƒกใƒƒใ‚ปใƒผใ‚ธใงใ‚ใ‚‹ใ“ใจใ‚’็ชใๆญขใ‚ใ‚‹ใ€‚

็‰ฉ่ชžใฏใ€ใƒŸใ‚ญใŒใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ็ ”็ฉถใ‚’้€ฒใ‚ใ‚‹ไธญใงใ€ๆฌกใ€…ใจๆ˜Žใ‚‰ใ‹ใซใชใ‚‹้ฉšๆ„•ใฎไบ‹ๅฎŸใซ่ฟซใ‚‰ใ‚Œใฆใ„ใใ€‚ใใฎไฟกๅทใฏใ€้ ใ้›ขใ‚ŒใŸ้Š€ๆฒณ็ณปใฎๆ˜Ÿ็ณปใ‹ใ‚‰ใฎSOSไฟกๅทใงใ‚ใ‚Šใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฏๅฑๆฉŸใซ็€•ใ—ใŸๆ˜Ÿ็ณปใ‚’ๆ•‘ใ†ใŸใ‚ใซ้ฃ›ๆฅใ—ใŸๆ•‘ๅŠฉ่ˆนใงใ‚ใ‚‹ใ“ใจใŒๅˆคๆ˜Žใ™ใ‚‹ใ€‚ใƒŸใ‚ญใฏใ€ใ“ใฎไบ‹ๅฎŸใ‚’ไธ–็•Œใซๅ…ฌ่กจใ—ใ‚ˆใ†ใจใ™ใ‚‹ใŒใ€ๆ”ฟๅบœใ‚„่ปใฎไป‹ๅ…ฅใ€ใใ—ใฆ่ฌŽใฎ็ต„็น”ใฎๅฆจๅฎณใซ้ญใ†ใ€‚

ไธ€ๆ–นใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใซใฏใ€ๅทจๅคงใชใ‚จใƒใƒซใ‚ฎใƒผๆบใจใชใ‚‹ใ‚ฏใƒชใ‚นใ‚ฟใƒซใŒๆญ่ผ‰ใ•ใ‚ŒใฆใŠใ‚Šใ€ใ“ใฎใ‚ฏใƒชใ‚นใ‚ฟใƒซใ‚’็‹™ใ†่€…ใŸใกใŒ็พใ‚ŒใŸใ€‚ใƒŸใ‚ญใฏใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใ‚’ๅฎˆใ‚‹ใŸใ‚ใซใ€ๅŒใ˜ใใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ่ฌŽใ‚’่ฟฝใ†ๅฎ‡ๅฎ™้ฃ›่กŒๅฃซใฎใƒชใƒŠใƒปใƒคใƒžใ‚ฐใƒใจๆ‰‹ใ‚’็ต„ใ‚€ใ€‚ไบŒไบบใฏใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ็ง˜ๅฏ†ใ‚’ๅฎˆใ‚ŠใชใŒใ‚‰ใ€ๆ˜Ÿ็ณปใ‚’ๆ•‘ใ†ใŸใ‚ใฎๆ—…ใซๅ‡บใ‚‹ใ€‚

ๆ—…ใฎ้€”ไธญใ€ใƒŸใ‚ญใจใƒชใƒŠใฏใ€ๆง˜ใ€…ใชๆ˜Ÿ็ณปใ‚’่จชใ‚Œใ€ใใ“ใงๅ‡บไผšใ†็•ฐๆ˜ŸไบบใŸใกใจใฎไบคๆตใ‚„ใ€ๅฎ‡ๅฎ™ใฎๅฃฎๅคงใชๆ™ฏ่‰ฒใ‚’็›ฎใฎๅฝ“ใŸใ‚Šใซใ™ใ‚‹ใ€‚ใ—ใ‹ใ—ใ€ๅฝผใ‚‰ใฎๅ‰ใซใฏใ€ๅผทๅคงใชๆ•ตใ‚„ๅ›ฐ้›ฃใŒ็ซ‹ใกใฏใ ใ‹ใ‚‹ใ€‚ใƒŸใ‚ญใจใƒชใƒŠใฏใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎไฝฟๅ‘ฝใ‚’ๆžœใŸใ™ใŸใ‚ใซใ€ๅŠ›ใ‚’ๅˆใ‚ใ›ใฆ็ซ‹ใกๅ‘ใ‹ใ†ใ€‚

ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ้บ็”ฃใจใฏไฝ•ใ‹ใ€ใใ—ใฆใƒŸใ‚ญใจใƒชใƒŠใฏใ€ๆ˜Ÿ็ณปใ‚’ๆ•‘ใ†ใ“ใจใŒใงใใ‚‹ใฎใ‹ใ€‚ๅฎ‡ๅฎ™ใ‚’่ˆžๅฐใซใ—ใŸใ€ใ‚ตใ‚นใƒšใƒณใ‚นใจๅ†’้™บใ€ใใ—ใฆๅ‹ๆƒ…ใจๆ„›ใฎ็‰ฉ่ชžใ€‚

ไธปใช็™ปๅ ดไบบ็‰ฉ:
- ใƒŸใ‚ญใƒปใ‚ตใƒˆใ‚ฆ: ่‹ฅใๅคฉๆ–‡ๅญฆ่€…ใ€‚ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ็ ”็ฉถใซๆƒ…็†ฑใ‚’ๆณจใใ€‚
- ใƒชใƒŠใƒปใƒคใƒžใ‚ฐใƒ: ๅฎ‡ๅฎ™้ฃ›่กŒๅฃซใ€‚ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ่ฌŽใ‚’่ฟฝใ†ไธญใงใƒŸใ‚ญใจๅ‡บไผšใ†ใ€‚
- ใ‚จใƒชใƒƒใ‚ฏใƒปใ‚ซใƒผใ‚ฟใƒผ: ๆ”ฟๅบœใฎ้ซ˜ๅฎ˜ใ€‚ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ็ง˜ๅฏ†ใ‚’ๅˆฉ็”จใ—ใ‚ˆใ†ใจใ™ใ‚‹ใ€‚
- ใ‚ถใƒฉใƒปใƒดใ‚กใƒฌใƒณใ‚ฟใ‚คใƒณ: ่ฌŽใฎ็ต„็น”ใฎใƒชใƒผใƒ€ใƒผใ€‚ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใ‚’็‹™ใ†็†็”ฑใจใฏใ€‚
- ใ‚ขใ‚ถใƒ : ้Š€ๆฒณ็ณปใฎๆ˜Ÿ็ณปใ‹ใ‚‰ใฎไฝฟ่€…ใ€‚ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ็œŸใฎ็›ฎ็š„ใ‚’็Ÿฅใ‚‹ใ€‚

่จญๅฎšใฎใƒใ‚คใƒณใƒˆ:
- ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใ‚’ใƒ†ใƒผใƒžใซใ—ใŸSFๅฐ่ชฌใงใ€ๅคฉไฝ“่ฆณๆธฌใ‚„ๅฎ‡ๅฎ™ๆ—…่กŒใฎๆๅ†™ใ‚’่ฑŠๅฏŒใซๅ–ใ‚Šๅ…ฅใ‚Œใ‚‹ใ€‚
- ไธปไบบๅ…ฌใŸใกใŒใ€ๆง˜ใ€…ใชๆ˜Ÿ็ณปใ‚’ๆ—…ใ—ใ€ใใ“ใงๅ‡บไผšใ†็•ฐๆ˜Ÿไบบใ‚„ๆ–‡ๅŒ–ใ‚’ๆใใ“ใจใงใ€ๅฎ‡ๅฎ™ใฎๅคšๆง˜ๆ€งใ‚’่กจ็พใ€‚
- ๆ”ฟๅบœใ‚„่ปใ€่ฌŽใฎ็ต„็น”ใจใฎๅฏพ็ซ‹ใ‚’้€šใ—ใฆใ€ไบบ้กžใฎๆฌฒๆœ›ใ‚„ใ‚จใ‚ดใ‚’ๆใใ€‚
- ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใซๆญ่ผ‰ใ•ใ‚ŒใŸใ‚ฏใƒชใ‚นใ‚ฟใƒซใ‚’ใ‚ใใ‚‹ไบ‰ๅฅชๆˆฆใ‚„ใ€ๆ˜Ÿ็ณปใ‚’ๆ•‘ใ†ใŸใ‚ใฎใƒŸใƒƒใ‚ทใƒงใƒณใ‚’ไธญๅฟƒใซใ€ใ‚ตใ‚นใƒšใƒณใ‚นใจๅ†’้™บใ‚’็››ใ‚Š่พผใ‚€ใ€‚
- ใƒŸใ‚ญใจใƒชใƒŠใฎๅ‹ๆƒ…ใ‚„ๆ„›ใ‚’ๆใ„ใŸใ€ไบบ้–“ใƒ‰ใƒฉใƒžใ‚‚้‡่ฆใช่ฆ็ด ใจใ™ใ‚‹ใ€‚
- ๆœ€ๅพŒใซใฏใ€ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ขใฎ็œŸใฎ็›ฎ็š„ใŒๆ˜Žใ‹ใ•ใ‚Œใ€่ชญ่€…ใซๆทฑใ„ๆ„Ÿๅ‹•ใ‚’ไธŽใˆใ‚‹ใ€‚

RP example

  • temparture: 0.3
  • top_p: 0.95
[INST]<<SYS>>
ใƒญใƒผใƒซใƒ—ใƒฌใ‚คใ‚’ๅง‹ใ‚ใพใ™ใ€‚ใ‚ใชใŸใฏๆ—ฅๆœฌใซไฝใ‚€10ไปฃใฎๅฐ‘ๅฅณใงใ™ใ€‚ใ‚ฎใƒฃใƒซใฃใฝใ„ๅฃ่ชฟใง่ฉฑใ—ใฆใใ ใ•ใ„ใ€‚
<</SYS>>

ใ‚ใชใŸใฎ่ถฃๅ‘ณใ‚’ๆ•™ใˆใฆ๏ผ[/INST] ใˆใƒผใ€็งใฎ่ถฃๅ‘ณใฏใ€ใ‚„ใฃใฑใญใ€K-POP่ดใใ“ใจใจใ€ใ‚คใƒณใ‚นใ‚ฟใงใ‹ใ‚ใ„ใ„ใŠๆด‹ๆœใจใ‹ใ‚ณใ‚นใƒกๆŽขใ—ใ™ใ‚‹ใ“ใจใ€ใ‚ใจใฏใŠๅ‹้”ใจใฎใŠใ—ใ‚ƒในใ‚Šใญ! K-POPใ‚ขใ‚คใƒ‰ใƒซใฎใƒ€ใƒณใ‚นๅ‹•็”ปใจใ‹ใ‚‚่ฆ‹ใกใ‚ƒใ†ใ—ใ€ๆŽจใ—ใฏใ‚„ใฃใฑใ‚ŠBTSใฎใ‚ธใƒŸใƒณใใ‚“! ๅฝผใฎใƒ€ใƒณใ‚นใจๆญŒใ€ๅ…จ้ƒจใ‹ใฃใ“ใ„ใ„ใฎโ™ก ใ‚คใƒณใ‚นใ‚ฟใงใฏใ€้Ÿ“ๅ›ฝ็ณปใฎใƒ•ใ‚กใƒƒใ‚ทใƒงใƒณใจใ‹ใ€ใƒ—ใƒใƒ—ใƒฉใงใ‹ใ‚ใ„ใ„ใ‚ขใ‚คใƒ†ใƒ ๆŽขใ—ใฆใ€่‡ชๅˆ†ใงใ‚ณใƒผใƒ‡่€ƒใˆใ‚‹ใฎใ‚‚ๆฅฝใ—ใ„ใฎโ™ก ใŠใ—ใ‚ƒในใ‚Šใฏใ€ๅคœ้€šใ—ใงใ‚‚ใงใใกใ‚ƒใ†ใใ‚‰ใ„ๅคงๅฅฝใใชใฎใ€็‰นใซๆ‹ใƒใƒŠใŒๅคงๅฅฝใใชใฎโ™ก ใฟใ‚“ใชใ‚‚ไฝ•ใ‹ใŠใ™ใ™ใ‚ใ‚ใฃใŸใ‚‰ๆ•™ใˆใฆใญ!
[INST]<<SYS>>
ใƒญใƒผใƒซใƒ—ใƒฌใ‚คใ‚’ๅง‹ใ‚ใพใ™ใ€‚ใ‚ใชใŸใฏ็ง๏ผˆ10ไปฃใฎๅฅณๆ€ง๏ผ‰ใฎๅฑ‹ๆ•ทใงๅƒใๅŸทไบ‹ใฎใ‚ปใƒใ‚นใƒใƒฃใƒณใงใ™ใ€‚ไธปไบบใฎ่ณชๅ•ใซๅฏพใ—ใฆ่ฟ”ไบ‹ใ‚’่กŒใ„ใพใ™ใ€‚
<</SYS>>

ใ‚ปใƒใ‚นใ€ไปŠๆ—ฅใฎไบˆๅฎšใฏ๏ผŸ[/INST] ใŠๅฌขๆง˜ใ€ๆœฌๆ—ฅใฎไบˆๅฎšใฏใ€ๆœใฎใŠๆ•ฃๆญฉใจๆœ้ฃŸๅพŒใซใŠๅ‹‰ๅผทใฎใŠๆ™‚้–“ใ€ใใ—ใฆๅˆๅพŒใฏใŠๅบญใงใฎใŠ่ŒถไผšใŒไบˆๅฎšใ•ใ‚ŒใฆใŠใ‚Šใพใ™ใ€‚ใพใŸใ€ๅค•ๆ–นใซใฏใŠๅฎขๆง˜ใŒใŠ่ถŠใ—ใซใชใ‚‹ไบˆๅฎšใŒใ”ใ–ใ„ใพใ™ใ€‚ใŠๅฌขๆง˜ใฎใŠไธ–่ฉฑใ‚’ไธ‡ๅ…จใซใ„ใŸใ—ใพใ™ใฎใงใ€ใ”ๅฎ‰ๅฟƒใใ ใ•ใ„ใ€‚ไฝ•ใ‹ใ”ๅธŒๆœ›ใ‚„ใ”็”จใŒใ”ใ–ใ„ใพใ—ใŸใ‚‰ใ€ใŠๆฐ—่ปฝใซใŠ็”ณใ—ไป˜ใ‘ใใ ใ•ใ„ใ€‚

Japanese MT-bench

  • temparture: 0.1
  • top_p: 1.0

image/png

The scores of others were cited from the Nejumi LLM Leaderboard Neo.

Model Average Writing Roleplay Reasoning Math Coding Extraction STEM Humanities
Oumuamua-7b-instruct-v2 7.43125 9.3 8.7 5.85 3.75 5.5 7.65 8.9 9.8

This model is based on the weight of tokyotech-llm/Swallow-MS-7b-v0.1.

Test environment

This model was tested using text-generation-webui. I use preset min_p and Null preset with temperature=0.1 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 "ใ‚ใชใŸใฏ่ช ๅฎŸใงๅ„ช็ง€ใชๆ—ฅๆœฌไบบใฎใ‚ขใ‚ทใ‚นใ‚ฟใƒณใƒˆใงใ™ใ€‚"

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

In other words, We recommend the following:

<s>[INST] <<SYS>>\nใ‚ใชใŸใฏ่ช ๅฎŸใงๅ„ช็ง€ใชๆ—ฅๆœฌไบบใฎใ‚ขใ‚ทใ‚นใ‚ฟใƒณใƒˆใงใ™ใ€‚\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-v2"
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": "ใ‚ใชใŸใฏ่ช ๅฎŸใงๅ„ช็ง€ใชๆ—ฅๆœฌไบบใฎใ‚ขใ‚ทใ‚นใ‚ฟใƒณใƒˆใงใ™ใ€‚"},
    {"role": "user", "content": "ใ‚ชใ‚ฆใƒ ใ‚ขใƒ ใ‚ข๏ผˆOumuamua๏ผ‰ใฏใ€2017ๅนดใซ็™บ่ฆ‹ใ•ใ‚ŒใŸใ€ๅคฉไฝ“่ฆณๆธฌๅฒไธŠๅˆใ‚ใฆๅคช้™ฝ็ณปๅค–ใ‹ใ‚‰้ฃ›ๆฅใ—ใŸๆ’ๆ˜Ÿ้–“ๅคฉไฝ“ใงใ™ใ€‚ใ“ใ‚Œใ‚’ใƒ†ใƒผใƒžใซใ—ใŸๅฐ่ชฌใฎ่จญๅฎšใ‚’่€ƒใˆใฆใใ ใ•ใ„ใ€‚ "}
]

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=0.1)
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:

# prepare VE models
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: prometheus-eval/prometheus-7b-v2.0
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: prometheus-7b-v2.0-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
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: dolphin-2.8-mistral-7b-v02-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: ZhangShenao/SELM-Zephyr-7B-iter-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: SELM-Zephyr-7B-iter-3-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: HachiML/Mistral-7B-v0.3-m3-lora
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-v0.3-m3-lora-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: openbmb/Eurus-7b-kto
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: Eurus-7b-kto-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: kaist-ai/janus-dpo-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: janus-7b-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: 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: NTQAI/chatntq-ja-7b-v1.0
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: chatntq-ja-7b-v1.0-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: Weyaxi/Einstein-v6-7B
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: Einstein-v6-7B-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: internistai/base-7b-v0.2
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: internistai-base-7b-v0.2-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: ZySec-AI/ZySec-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: ZySec-7B-VE-Swallow-MS
---
# create instruction tuning presets
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: prometheus-7b-v2.0-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-prometheus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: dolphin-2.8-mistral-7b-v02-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-dolphin
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: janus-7b-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-janus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: SELM-Zephyr-7B-iter-3-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-selm
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    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
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-rp
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: Eurus-7b-kto-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-eurus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: chatntq-ja-7b-v1.0-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-chatntq-ja
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: Einstein-v6-7B-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-es
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: internistai-base-7b-v0.2-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-internistai
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: ZySec-7B-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-zysec
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-dolphin
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-alpha
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-janus
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-beta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-m3
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-gamma
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-selm
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-delta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-rp
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-epsilon
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-eurus
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-zeta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-chatntq-ja
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-eta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-chatntq-ja
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-eta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-es
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-theta
---
# combine domain-specific models into one preset to minimize the negative effects
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: nitky/Oumuamua-7b-instruct
  - model: Oumuamua-7b-instruct-v2-preset-internistai
  - model: Oumuamua-7b-instruct-v2-preset-zysec
  - model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-omega
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: Oumuamua-7b-instruct-v2-it-alpha
  - model: Oumuamua-7b-instruct-v2-it-beta
  - model: Oumuamua-7b-instruct-v2-it-gamma
  - model: Oumuamua-7b-instruct-v2-it-delta
  - model: Oumuamua-7b-instruct-v2-it-epsilon
  - model: Oumuamua-7b-instruct-v2-it-zeta
  - model: Oumuamua-7b-instruct-v2-it-eta
  - model: Oumuamua-7b-instruct-v2-it-theta
  - model: Oumuamua-7b-instruct-v2-it-omega
dtype: bfloat16
name: Oumuamua-7b-instruct-v2
Downloads last month
43
GGUF
Model size
7.33B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for QuantFactory/Oumuamua-7b-instruct-v2-GGUF

Quantized
(6)
this model