metadata

language:
  - en
  - ko
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0

SOLAR-tail-10.7B-Merge-v1.0

Model Details

Model Developers Kyujin Han (kyujinpy)

Method
Using Mergekit.

Merge config

slices:
  - sources:
      - model: upstage/SOLAR-10.7B-v1.0
        layer_range: [0, 48]
      - model: Yhyu13/LMCocktail-10.7B-v1
        layer_range: [0, 48]
        
merge_method: slerp
base_model: upstage/SOLAR-10.7B-v1.0

parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
tokenizer_source: union
    
dtype: float16

Model Benchmark

Open Ko leaderboard

Follow up as Ko-link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Ko-CommonGenV2
PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0	NaN	NaN	NaN	NaN	NaN	NaN
jjourney1125/M-SOLAR-10.7B-v1.0	55.15	49.57	60.12	54.60	49.23	62.22
beomi/Yi-Ko-6B	48.79	41.04	53.39	46.28	41.64	61.63
mistralai/Mistral-7B-v0.1	46.89	38.14	48.19	45.20	46.13	56.79

Follow up as En-link.

lm-evaluation-harness

gpt2 (pretrained=PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|      Task      |Version| Metric |Value |   |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq    |      0|acc     |0.5021|±  |0.0133|
|                |       |macro_f1|0.3343|±  |0.0059|
|kobest_copa     |      0|acc     |0.6220|±  |0.0153|
|                |       |macro_f1|0.6217|±  |0.0154|
|kobest_hellaswag|      0|acc     |0.4380|±  |0.0222|
|                |       |acc_norm|0.5380|±  |0.0223|
|                |       |macro_f1|0.4366|±  |0.0222|
|kobest_sentineg |      0|acc     |0.4962|±  |0.0251|
|                |       |macro_f1|0.3316|±  |0.0113|

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)