You can deploy this model and start earning money today!

RichardErkhov/
Nitral-AI_-_Pasta-Lake-7b-gguf

Name: Nitral-AI_-_Pasta-Lake-7b-gguf
Rating: 2.5 (46 reviews)

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Pasta-Lake-7b - GGUF

Model creator: https://huggingface.co/Nitral-AI/
Original model: https://huggingface.co/Nitral-AI/Pasta-Lake-7b/

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

Original model description:

license: other library_name: transformers tags:

mergekit
merge base_model:
Test157t/Pasta-PrimaMaid-7b
macadeliccc/WestLake-7B-v2-laser-truthy-dpo model-index:
name: Pasta-Lake-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: 70.82 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 87.91 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 64.41 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 68.28 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 82.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 64.37 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-7b name: Open LLM Leaderboard

Thanks to @Kooten the man the myth the legend we have exl2 quants: https://huggingface.co/models?search=Kooten/Pasta-Lake-7b-exl2

Thanks to @bartowski the homie for the additional exl2 quants, please show him some support aswell: https://huggingface.co/bartowski/Pasta-Lake-7b-exl2/tree/main

Thanks also to @konz00 for the gguf quants: https://huggingface.co/konz00/Pasta-Lake-7b-GGUF

Thanks to @Lewdiculus for the other GGUF quants: https://huggingface.co/Lewdiculous/Pasta-Lake-7b-GGUF

added ST preset files

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: Test157t/Pasta-PrimaMaid-7b
        layer_range: [0, 32]
      - model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
        layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Pasta-PrimaMaid-7b
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
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.07
AI2 Reasoning Challenge (25-Shot)	70.82
HellaSwag (10-Shot)	87.91
MMLU (5-Shot)	64.41
TruthfulQA (0-shot)	68.28
Winogrande (5-shot)	82.64
GSM8k (5-shot)	64.37

RichardErkhov/Nitral-AI_-_Pasta-Lake-7b-gguf

Original model description:

Models Merged

Configuration

Open LLM Leaderboard Evaluation Results

RichardErkhov/
Nitral-AI_-_Pasta-Lake-7b-gguf