Megakiqu-120b

megakiqu-120B MegaDolphin-120B๋‚˜ Venus-120B๊ณผ ์œ ์‚ฌํ•˜๊ฒŒ passthrough method๋กœ ํ™•์žฅ๋œ ๋ชจ๋ธ.

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Original Model Card

kiqu-70b (Arena Leaderboard)

kiqu-70b is a SFT+DPO trained model based on Miqu-70B-Alpaca-DPO using Korean datasets.

Since this model is finetune of miqu-1-70b using it on commercial purposes is at your own risk. โ€” leaked early version Mistral-Medium

๋ณธ ๋ชจ๋ธ kiqu-70b๋Š” Miqu-70B-Alpaca-DPO ๋ชจ๋ธ์„ ๊ธฐ๋ฐ˜์œผ๋กœ ํ•œ๊ตญ์–ด ๋ฐ์ดํ„ฐ์…‹์„ ์‚ฌ์šฉํ•˜์—ฌ SFT+DPO ํ›ˆ๋ จ์„ ์ง„ํ–‰ํ•˜์—ฌ ์ œ์ž‘๋˜์—ˆ์Šต๋‹ˆ๋‹ค.

๋ฒ ์ด์Šค ๋ชจ๋ธ์ธ miqu-1-70b ๋ชจ๋ธ์ด ๋ฏธ์ŠคํŠธ๋ž„-๋ฏธ๋””์›€์˜ ์ดˆ๊ธฐ ์œ ์ถœ ๋ฒ„์ „์ด๊ธฐ์— ์ƒ์—…์  ์‚ฌ์šฉ์— ๋Œ€ํ•œ risk๋Š” ๋ณธ์ธ์—๊ฒŒ ์žˆ์Šต๋‹ˆ๋‹ค.

Beside that this model follows cc-by-sa-4.0

๋ณธ ๋ชจ๋ธ ์ž์ฒด๋กœ์„œ๋Š” cc-by-sa-4.0์„ ๋”ฐ๋ฆ…๋‹ˆ๋‹ค.

Model Details

Base Model
miqu-1-70b (Early Mistral-Medium)

Instruction format

It follows Mistral format. Giving few-shots to model is highly recommended

๋ณธ ๋ชจ๋ธ์€ ๋ฏธ์ŠคํŠธ๋ž„ ํฌ๋งท์„ ๋”ฐ๋ฆ…๋‹ˆ๋‹ค. few-shot ์‚ฌ์šฉ์„ ์ ๊ทน ๊ถŒ์žฅํ•ฉ๋‹ˆ๋‹ค.

[INST] {instruction}
[/INST] {output}

Multi-shot

[INST] {instruction}
[/INST] {output}
[INST] {instruction}
[/INST] {output}
[INST] {instruction}
[/INST] {output}
.
.
.

Recommended Template - 1-shot with system prompt

๋„ˆ๋Š” kiqu-70B๋ผ๋Š” ํ•œ๊ตญ์–ด์— ํŠนํ™”๋œ ์–ธ์–ด๋ชจ๋ธ์ด์•ผ. ๊น”๋”ํ•˜๊ณ  ์ž์—ฐ์Šค๋Ÿฝ๊ฒŒ ๋Œ€๋‹ตํ•ด์ค˜!
[INST] ์•ˆ๋…•?
[/INST] ์•ˆ๋…•ํ•˜์„ธ์š”! ๋ฌด์—‡์„ ๋„์™€๋“œ๋ฆด๊นŒ์š”? ์งˆ๋ฌธ์ด๋‚˜ ๊ถ๊ธˆํ•œ ์ ์ด ์žˆ๋‹ค๋ฉด ์–ธ์ œ๋“ ์ง€ ๋ง์”€ํ•ด์ฃผ์„ธ์š”.
[INST] {instruction}
[/INST]

Trailing space after [/INST] can affect models performance in significant margin. So, when doing inference it is recommended to not include trailing space in chat template.

[/INST] ๋’ค์— ๋„์–ด์“ฐ๊ธฐ๋Š” ๋ชจ๋ธ ์„ฑ๋Šฅ์— ์œ ์˜๋ฏธํ•œ ์˜ํ–ฅ์„ ๋ฏธ์นฉ๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ, ์ธํผ๋Ÿฐ์Šค(์ถ”๋ก )๊ณผ์ •์—์„œ๋Š” ์ฑ— ํ…œํ”Œ๋ฆฟ์— ๋„์–ด์“ฐ๊ธฐ๋ฅผ ์ œ์™ธํ•˜๋Š” ๊ฒƒ์„ ์ ๊ทน ๊ถŒ์žฅํ•ฉ๋‹ˆ๋‹ค.

Configuration

The following mergekit's YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 20]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [10, 30]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [20, 40]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [30, 50]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [40, 60]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [50, 70]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [60, 80]
    model: maywell/kiqu-70b
Downloads last month
20
Safetensors
Model size
120B params
Tensor type
BF16
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kuotient/Megakiqu-120b

Base model

maywell/kiqu-70b
Finetuned
(1)
this model
Quantizations
2 models