You can deploy this model and start earning money today!

RichardErkhov/
Inv_-_Konstanta-Alpha-V2-7B-gguf

Name: Inv_-_Konstanta-Alpha-V2-7B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Konstanta-Alpha-V2-7B - GGUF

Model creator: https://huggingface.co/Inv/
Original model: https://huggingface.co/Inv/Konstanta-Alpha-V2-7B/

Name	Quant method	Size
Konstanta-Alpha-V2-7B.Q2_K.gguf	Q2_K	2.53GB
Konstanta-Alpha-V2-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Konstanta-Alpha-V2-7B.IQ3_S.gguf	IQ3_S	2.96GB
Konstanta-Alpha-V2-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Konstanta-Alpha-V2-7B.IQ3_M.gguf	IQ3_M	3.06GB
Konstanta-Alpha-V2-7B.Q3_K.gguf	Q3_K	3.28GB
Konstanta-Alpha-V2-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Konstanta-Alpha-V2-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Konstanta-Alpha-V2-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Konstanta-Alpha-V2-7B.Q4_0.gguf	Q4_0	3.83GB
Konstanta-Alpha-V2-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Konstanta-Alpha-V2-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Konstanta-Alpha-V2-7B.Q4_K.gguf	Q4_K	4.07GB
Konstanta-Alpha-V2-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Konstanta-Alpha-V2-7B.Q4_1.gguf	Q4_1	4.24GB
Konstanta-Alpha-V2-7B.Q5_0.gguf	Q5_0	4.65GB
Konstanta-Alpha-V2-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Konstanta-Alpha-V2-7B.Q5_K.gguf	Q5_K	4.78GB
Konstanta-Alpha-V2-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Konstanta-Alpha-V2-7B.Q5_1.gguf	Q5_1	5.07GB
Konstanta-Alpha-V2-7B.Q6_K.gguf	Q6_K	5.53GB
Konstanta-Alpha-V2-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

language:

en license: apache-2.0 library_name: transformers tags:
mergekit
merge
mistralai/Mistral-7B-v0.1
SanjiWatsuki/Kunoichi-DPO-v2-7B
maywell/PiVoT-0.1-Evil-a
mlabonne/ArchBeagle-7B
LakoMoor/Silicon-Alice-7B
roleplay
rp
not-for-all-audiences base_model:
mistralai/Mistral-7B-v0.1
SanjiWatsuki/Kunoichi-DPO-v2-7B
maywell/PiVoT-0.1-Evil-a
mlabonne/ArchBeagle-7B
LakoMoor/Silicon-Alice-7B model-index:
name: Konstanta-Alpha-V2-7B 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=Inv/Konstanta-Alpha-V2-7B 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: 87.14 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B 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: 65.11 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B 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: 61.08 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B 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=Inv/Konstanta-Alpha-V2-7B 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: 69.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B name: Open LLM Leaderboard

Konstanta-Alpha-V2-7B

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES to merge Kunoichi with PiVoT Evil and to merge ArchBeagle with Silicon Alice, and then merge the resulting 2 models with the gradient SLERP merge method. ChatML seems to work the best.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model (to reproduce use mergekit-mega command):

yaml

base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: dare_ties
parameters:
  int8_mask: true
slices:
- sources:
  - layer_range: [0, 32]
    model: mistralai/Mistral-7B-v0.1
  - layer_range: [0, 32]
    model: : SanjiWatsuki/Kunoichi-DPO-v2-7B
    parameters:
      density: 0.8
      weight: 0.5
  - layer_range: [0, 32]
    model: : maywell/PiVoT-0.1-Evil-a
    parameters:
      density: 0.3
      weight: 0.15
name: first-step
---
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: dare_ties
parameters:
  int8_mask: true
slices:
- sources:
  - layer_range: [0, 32]
    model: mistralai/Mistral-7B-v0.1
  - layer_range: [0, 32]
    model: mlabonne/ArchBeagle-7B
    parameters:
      density: 0.8
      weight: 0.75
  - layer_range: [0, 32]
    model: LakoMoor/Silicon-Alice-7B
    parameters:
      density: 0.6
      weight: 0.30
name: second-step
---
models:
   - model: first-step
   - model: second-step
merge_method: slerp
base_model: first-step
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
  int8_mask: true
  normalize: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.35
AI2 Reasoning Challenge (25-Shot)	69.62
HellaSwag (10-Shot)	87.14
MMLU (5-Shot)	65.11
TruthfulQA (0-shot)	61.08
Winogrande (5-shot)	81.22
GSM8k (5-shot)	69.90

RichardErkhov/Inv_-_Konstanta-Alpha-V2-7B-gguf