language:
- en
license: other
library_name: transformers
tags:
- text-generation-inference
- merge
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
pipeline_tag: text-generation
model-index:
- name: CapyTessBorosYi-34B-200K-DARE-Ties
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 64.93
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 85.92
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 76.18
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 55.84
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 83.03
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 61.94
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
name: Open LLM Leaderboard
Obsolete, see: https://huggingface.co/brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity
NousResearch/Nous-Capybara-34B, migtissera/Tess-M-v1.3 and bhenrym14/airoboros-3_1-yi-34b-200k merged with a new, experimental implementation of "dare ties" via mergekit. See:
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
https://github.com/yule-BUAA/MergeLM
https://github.com/cg123/mergekit/tree/dare'
Merged with the following config, and the tokenizer from chargoddard's Yi-Llama:
models:
- model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
# no parameters necessary for base model
- model: /home/alpha/Storage/Models/Raw/migtissera_Tess-M-v1.3
parameters:
weight: 0.41
density: 0.50
- model: /home/alpha//Storage/Models/Raw/bhenrym14_airoboros-3_1-yi-34b-200k
parameters:
weight: 0.18
density: 0.46
- model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B
parameters:
weight: 0.41
density: 0.50
merge_method: dare_ties
base_model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
parameters:
int8_mask: true
dtype: bfloat16
dare_ties is testing with better perplexity than a regular ties merge with the same merge configuration. Model weights that add up to one also seem optimal from testing. And high context results seem... better than the previous dare merge with Tess 1.2.
I chose not to include other finetunes, such as Dolphin, because they aren't trained on the 200K base. If any other 200K finetunes pop up, let me know.
Prompt template: Orca-Vicuna
SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
Being a Yi model, try disabling the BOS token and/or running a lower temperature with MinP (and no other samplers) if output doesn't seem right. Yi tends to run "hot" by default.
Sometimes the model "spells out" the stop token as </s> like Capybara, so you may need to add </s> as an additional stopping condition. It also might respond to the llama-2 chat format.
24GB GPUs can run Yi-34B-200K models at 45K-75K context with exllamav2. I go into more detail in this post, and recommend exl2 quantizations on data similar to the desired task, such as these targeted at story writing: 4.0bpw / 3.1bpw
Credits:
https://github.com/cg123/mergekit/tree/dare
https://huggingface.co/NousResearch/Nous-Capybara-34B/
https://huggingface.co/bhenrym14/airoboros-3_1-yi-34b-200k
https://huggingface.co/migtissera/Tess-M-v1.3
https://huggingface.co/chargoddard/Yi-34B-200K-Llama
https://huggingface.co/01-ai/Yi-34B-200K
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 71.31 |
| AI2 Reasoning Challenge (25-Shot) | 64.93 |
| HellaSwag (10-Shot) | 85.92 |
| MMLU (5-Shot) | 76.18 |
| TruthfulQA (0-shot) | 55.84 |
| Winogrande (5-shot) | 83.03 |
| GSM8k (5-shot) | 61.94 |