You can deploy this model and start earning money today!

RichardErkhov/
ibndias_-_Nous-Hermes-2-MoE-2x34B-gguf

Name: ibndias_-_Nous-Hermes-2-MoE-2x34B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Nous-Hermes-2-MoE-2x34B - GGUF

Model creator: https://huggingface.co/ibndias/
Original model: https://huggingface.co/ibndias/Nous-Hermes-2-MoE-2x34B/

Name	Quant method	Size
Nous-Hermes-2-MoE-2x34B.Q2_K.gguf	Q2_K	20.86GB
Nous-Hermes-2-MoE-2x34B.Q3_K_S.gguf	Q3_K_S	24.51GB
Nous-Hermes-2-MoE-2x34B.Q3_K.gguf	Q3_K	27.23GB
Nous-Hermes-2-MoE-2x34B.Q3_K_M.gguf	Q3_K_M	27.23GB
Nous-Hermes-2-MoE-2x34B.Q3_K_L.gguf	Q3_K_L	29.59GB
Nous-Hermes-2-MoE-2x34B.IQ4_XS.gguf	IQ4_XS	26.59GB
Nous-Hermes-2-MoE-2x34B.Q4_0.gguf	Q4_0	31.98GB
Nous-Hermes-2-MoE-2x34B.IQ4_NL.gguf	IQ4_NL	32.27GB
Nous-Hermes-2-MoE-2x34B.Q4_K_S.gguf	Q4_K_S	32.22GB
Nous-Hermes-2-MoE-2x34B.Q4_K.gguf	Q4_K	32.38GB
Nous-Hermes-2-MoE-2x34B.Q4_K_M.gguf	Q4_K_M	34.14GB
Nous-Hermes-2-MoE-2x34B.Q4_1.gguf	Q4_1	35.49GB
Nous-Hermes-2-MoE-2x34B.Q5_0.gguf	Q5_0	39.0GB
Nous-Hermes-2-MoE-2x34B.Q5_K_S.gguf	Q5_K_S	39.0GB
Nous-Hermes-2-MoE-2x34B.Q5_K.gguf	Q5_K	40.12GB
Nous-Hermes-2-MoE-2x34B.Q5_K_M.gguf	Q5_K_M	40.12GB
Nous-Hermes-2-MoE-2x34B.Q5_1.gguf	Q5_1	42.51GB
Nous-Hermes-2-MoE-2x34B.Q6_K.gguf	Q6_K	17.31GB
Nous-Hermes-2-MoE-2x34B.Q8_0.gguf	Q8_0	60.18GB

Original model description:

license: apache-2.0 model-index:

name: Nous-Hermes-2-MoE-2x34B 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: 66.64 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B 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: 85.73 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B 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: 76.49 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B 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: 58.08 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B 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: 83.35 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B 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: 69.52 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B name: Open LLM Leaderboard

This is an experimental model to make an MoE of Nous Hermes 2 Yi 34B as Mixture of Expert.

The base model is Yi-34B.

All credits belong to NousResearch for fine tuned Yi model, 01-AI for Yi model, and Charles O. Goddard for the 'mergekit'.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.30
AI2 Reasoning Challenge (25-Shot)	66.64
HellaSwag (10-Shot)	85.73
MMLU (5-Shot)	76.49
TruthfulQA (0-shot)	58.08
Winogrande (5-shot)	83.35
GSM8k (5-shot)	69.52

RichardErkhov/ibndias_-_Nous-Hermes-2-MoE-2x34B-gguf

Original model description:

Open LLM Leaderboard Evaluation Results

RichardErkhov/
ibndias_-_Nous-Hermes-2-MoE-2x34B-gguf