You can deploy this model and start earning money today!

RichardErkhov/
mixtao_-_MixTAO-7Bx2-MoE-v8.1-gguf

Name: mixtao_-_MixTAO-7Bx2-MoE-v8.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MixTAO-7Bx2-MoE-v8.1 - GGUF

Model creator: https://huggingface.co/mixtao/
Original model: https://huggingface.co/mixtao/MixTAO-7Bx2-MoE-v8.1/

Name	Quant method	Size
MixTAO-7Bx2-MoE-v8.1.Q2_K.gguf	Q2_K	4.43GB
MixTAO-7Bx2-MoE-v8.1.IQ3_XS.gguf	IQ3_XS	4.95GB
MixTAO-7Bx2-MoE-v8.1.IQ3_S.gguf	IQ3_S	5.22GB
MixTAO-7Bx2-MoE-v8.1.Q3_K_S.gguf	Q3_K_S	5.2GB
MixTAO-7Bx2-MoE-v8.1.IQ3_M.gguf	IQ3_M	5.35GB
MixTAO-7Bx2-MoE-v8.1.Q3_K.gguf	Q3_K	5.78GB
MixTAO-7Bx2-MoE-v8.1.Q3_K_M.gguf	Q3_K_M	5.78GB
MixTAO-7Bx2-MoE-v8.1.Q3_K_L.gguf	Q3_K_L	6.27GB
MixTAO-7Bx2-MoE-v8.1.IQ4_XS.gguf	IQ4_XS	6.5GB
MixTAO-7Bx2-MoE-v8.1.Q4_0.gguf	Q4_0	6.78GB
MixTAO-7Bx2-MoE-v8.1.IQ4_NL.gguf	IQ4_NL	6.85GB
MixTAO-7Bx2-MoE-v8.1.Q4_K_S.gguf	Q4_K_S	6.84GB
MixTAO-7Bx2-MoE-v8.1.Q4_K.gguf	Q4_K	7.25GB
MixTAO-7Bx2-MoE-v8.1.Q4_K_M.gguf	Q4_K_M	7.25GB
MixTAO-7Bx2-MoE-v8.1.Q4_1.gguf	Q4_1	7.52GB
MixTAO-7Bx2-MoE-v8.1.Q5_0.gguf	Q5_0	8.26GB
MixTAO-7Bx2-MoE-v8.1.Q5_K_S.gguf	Q5_K_S	8.26GB
MixTAO-7Bx2-MoE-v8.1.Q5_K.gguf	Q5_K	8.51GB
MixTAO-7Bx2-MoE-v8.1.Q5_K_M.gguf	Q5_K_M	8.51GB
MixTAO-7Bx2-MoE-v8.1.Q5_1.gguf	Q5_1	9.01GB
MixTAO-7Bx2-MoE-v8.1.Q6_K.gguf	Q6_K	9.84GB
MixTAO-7Bx2-MoE-v8.1.Q8_0.gguf	Q8_0	12.75GB

Original model description:

license: apache-2.0 tags:

moe model-index:
name: MixTAO-7Bx2-MoE-v8.1 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: 73.81 name: normalized accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1 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: 89.22 name: normalized accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1 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: 64.92 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1 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: 78.57 source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1 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: 87.37 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1 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: 71.11 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1 name: Open LLM Leaderboard

MixTAO-7Bx2-MoE

MixTAO-7Bx2-MoE is a Mixture of Experts (MoE). This model is mainly used for large model technology experiments, and increasingly perfect iterations will eventually create high-level large language models.

Prompt Template (Alpaca)

### Instruction:
<prompt> (without the <>)
### Response:

🦒 Colab

Link	Info - Model Name
Open In Colab	MixTAO-7Bx2-MoE-v8.1
mixtao-7bx2-moe-v8.1.Q4_K_M.gguf	GGUF of MixTAO-7Bx2-MoE-v8.1 Only Q4_K_M in https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1-GGUF
Demo Space	https://huggingface.co/spaces/zhengr/MixTAO-7Bx2-MoE-v8.1/

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	77.50
AI2 Reasoning Challenge (25-Shot)	73.81
HellaSwag (10-Shot)	89.22
MMLU (5-Shot)	64.92
TruthfulQA (0-shot)	78.57
Winogrande (5-shot)	87.37
GSM8k (5-shot)	71.11

RichardErkhov/mixtao_-_MixTAO-7Bx2-MoE-v8.1-gguf