metadata
license: other
tags:
- yi
- moe
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
model-index:
- name: Yi-34Bx2-MoE-60B
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: 71.08
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B
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: 85.23
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B
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: 77.47
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B
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: 66.19
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B
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: 84.85
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B
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: 75.51
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B
name: Open LLM Leaderboard
UPDATE! GGUF Format is ready at cloudyu/Yi-34Bx2-MoE-60B-GGUF
Yi based MOE 2x34B with mixtral architecture
Highest score Model ranked by Open LLM Leaderboard (2024-01-11)
This is an English & Chinese MoE Model , slightly different with cloudyu/Mixtral_34Bx2_MoE_60B, and also based on
- [jondurbin/bagel-dpo-34b-v0.2]
- [SUSTech/SUS-Chat-34B]
gpu code example
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "cloudyu/Yi-34Bx2-MoE-60B"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
CPU example
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "cloudyu/Yi-34Bx2-MoE-60B"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.bfloat16, device_map='cpu'
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 76.72 |
| AI2 Reasoning Challenge (25-Shot) | 71.08 |
| HellaSwag (10-Shot) | 85.23 |
| MMLU (5-Shot) | 77.47 |
| TruthfulQA (0-shot) | 66.19 |
| Winogrande (5-shot) | 84.85 |
| GSM8k (5-shot) | 75.51 |