You can deploy this model and start earning money today!

RichardErkhov/
R136a1_-_InfinityKuno-2x7B-gguf

Name: R136a1_-_InfinityKuno-2x7B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

InfinityKuno-2x7B - GGUF

Model creator: https://huggingface.co/R136a1/
Original model: https://huggingface.co/R136a1/InfinityKuno-2x7B/

Name	Quant method	Size
InfinityKuno-2x7B.Q2_K.gguf	Q2_K	4.43GB
InfinityKuno-2x7B.IQ3_XS.gguf	IQ3_XS	4.95GB
InfinityKuno-2x7B.IQ3_S.gguf	IQ3_S	5.22GB
InfinityKuno-2x7B.Q3_K_S.gguf	Q3_K_S	5.2GB
InfinityKuno-2x7B.IQ3_M.gguf	IQ3_M	5.35GB
InfinityKuno-2x7B.Q3_K.gguf	Q3_K	5.78GB
InfinityKuno-2x7B.Q3_K_M.gguf	Q3_K_M	5.78GB
InfinityKuno-2x7B.Q3_K_L.gguf	Q3_K_L	6.27GB
InfinityKuno-2x7B.IQ4_XS.gguf	IQ4_XS	6.5GB
InfinityKuno-2x7B.Q4_0.gguf	Q4_0	6.78GB
InfinityKuno-2x7B.IQ4_NL.gguf	IQ4_NL	6.85GB
InfinityKuno-2x7B.Q4_K_S.gguf	Q4_K_S	6.84GB
InfinityKuno-2x7B.Q4_K.gguf	Q4_K	7.25GB
InfinityKuno-2x7B.Q4_K_M.gguf	Q4_K_M	7.25GB
InfinityKuno-2x7B.Q4_1.gguf	Q4_1	7.52GB
InfinityKuno-2x7B.Q5_0.gguf	Q5_0	8.26GB
InfinityKuno-2x7B.Q5_K_S.gguf	Q5_K_S	8.26GB
InfinityKuno-2x7B.Q5_K.gguf	Q5_K	8.51GB
InfinityKuno-2x7B.Q5_K_M.gguf	Q5_K_M	8.51GB
InfinityKuno-2x7B.Q5_1.gguf	Q5_1	9.01GB
InfinityKuno-2x7B.Q6_K.gguf	Q6_K	9.84GB
InfinityKuno-2x7B.Q8_0.gguf	Q8_0	12.75GB

Original model description:

language:

en license: apache-2.0 tags:
safetensors
mixtral
not-for-all-audiences
nsfw model-index:
name: InfinityKuno-2x7B 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: 69.62 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=R136a1/InfinityKuno-2x7B 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: 87.44 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=R136a1/InfinityKuno-2x7B 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: 64.49 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=R136a1/InfinityKuno-2x7B 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: 63.28 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=R136a1/InfinityKuno-2x7B 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: 82.72 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=R136a1/InfinityKuno-2x7B 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: 66.34 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=R136a1/InfinityKuno-2x7B name: Open LLM Leaderboard

InfinityKuno-2x7B

Experimental model from Endevor/InfinityRP-v1-7B and SanjiWatsuki/Kunoichi-DPO-v2-7B models. Merged to MoE model with 2x7B parameters.

Prompt format:

Alpaca, Extended Alpaca, Roleplay-Alpaca. (Use any Alpaca based prompt formatting and you should be fine.)

Switch: FP16 - GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.32
AI2 Reasoning Challenge (25-Shot)	69.62
HellaSwag (10-Shot)	87.44
MMLU (5-Shot)	64.49
TruthfulQA (0-shot)	63.28
Winogrande (5-shot)	82.72
GSM8k (5-shot)	66.34

RichardErkhov/R136a1_-_InfinityKuno-2x7B-gguf

Original model description:

InfinityKuno-2x7B

Prompt format:

Open LLM Leaderboard Evaluation Results

RichardErkhov/
R136a1_-_InfinityKuno-2x7B-gguf