Quantization made by Richard Erkhov.

Mixtral_7Bx2_MoE - GGUF

Model creator: https://huggingface.co/cloudyu/
Original model: https://huggingface.co/cloudyu/Mixtral_7Bx2_MoE/

Name	Quant method	Size
Mixtral_7Bx2_MoE.Q2_K.gguf	Q2_K	4.43GB
Mixtral_7Bx2_MoE.IQ3_XS.gguf	IQ3_XS	4.95GB
Mixtral_7Bx2_MoE.IQ3_S.gguf	IQ3_S	5.22GB
Mixtral_7Bx2_MoE.Q3_K_S.gguf	Q3_K_S	5.2GB
Mixtral_7Bx2_MoE.IQ3_M.gguf	IQ3_M	5.35GB
Mixtral_7Bx2_MoE.Q3_K.gguf	Q3_K	5.78GB
Mixtral_7Bx2_MoE.Q3_K_M.gguf	Q3_K_M	5.78GB
Mixtral_7Bx2_MoE.Q3_K_L.gguf	Q3_K_L	6.27GB
Mixtral_7Bx2_MoE.IQ4_XS.gguf	IQ4_XS	6.5GB
Mixtral_7Bx2_MoE.Q4_0.gguf	Q4_0	6.78GB
Mixtral_7Bx2_MoE.IQ4_NL.gguf	IQ4_NL	6.85GB
Mixtral_7Bx2_MoE.Q4_K_S.gguf	Q4_K_S	6.84GB
Mixtral_7Bx2_MoE.Q4_K.gguf	Q4_K	7.25GB
Mixtral_7Bx2_MoE.Q4_K_M.gguf	Q4_K_M	7.25GB
Mixtral_7Bx2_MoE.Q4_1.gguf	Q4_1	7.52GB
Mixtral_7Bx2_MoE.Q5_0.gguf	Q5_0	8.26GB
Mixtral_7Bx2_MoE.Q5_K_S.gguf	Q5_K_S	8.26GB
Mixtral_7Bx2_MoE.Q5_K.gguf	Q5_K	8.51GB
Mixtral_7Bx2_MoE.Q5_K_M.gguf	Q5_K_M	8.51GB
Mixtral_7Bx2_MoE.Q5_1.gguf	Q5_1	9.01GB
Mixtral_7Bx2_MoE.Q6_K.gguf	Q6_K	9.84GB
Mixtral_7Bx2_MoE.Q8_0.gguf	Q8_0	12.75GB

Original model description:

license: cc-by-nc-4.0 model-index: - name: Mixtral_7Bx2_MoE 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: 71.25 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE 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: 87.45 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE 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: 64.98 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE 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: 67.23 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE 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: 81.22 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE 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: 68.46 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE name: Open LLM Leaderboard

Mixtral MOE 2x7B

MoE of the following models :

NurtureAI/neural-chat-7b-v3-16k
mncai/mistral-7b-dpo-v6
metrics: Average 73.43 ARC 71.25 HellaSwag 87.45

gpu code example

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math

## v2 models
model_path = "cloudyu/Mixtral_7Bx2_MoE"

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/Mixtral_7Bx2_MoE"

tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
    model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False
)
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.	73.43
AI2 Reasoning Challenge (25-Shot)	71.25
HellaSwag (10-Shot)	87.45
MMLU (5-Shot)	64.98
TruthfulQA (0-shot)	67.23
Winogrande (5-shot)	81.22
GSM8k (5-shot)	68.46