You can deploy this model and start earning money today!

RichardErkhov/
sequelbox_-_Llama3.1-8B-PlumMath-gguf

Name: sequelbox_-_Llama3.1-8B-PlumMath-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama3.1-8B-PlumMath - GGUF

Model creator: https://huggingface.co/sequelbox/
Original model: https://huggingface.co/sequelbox/Llama3.1-8B-PlumMath/

Name	Quant method	Size
Llama3.1-8B-PlumMath.Q2_K.gguf	Q2_K	2.96GB
Llama3.1-8B-PlumMath.Q3_K_S.gguf	Q3_K_S	1.21GB
Llama3.1-8B-PlumMath.Q3_K.gguf	Q3_K	3.74GB
Llama3.1-8B-PlumMath.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama3.1-8B-PlumMath.Q3_K_L.gguf	Q3_K_L	0.01GB
Llama3.1-8B-PlumMath.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama3.1-8B-PlumMath.Q4_0.gguf	Q4_0	4.34GB
Llama3.1-8B-PlumMath.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama3.1-8B-PlumMath.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama3.1-8B-PlumMath.Q4_K.gguf	Q4_K	4.58GB
Llama3.1-8B-PlumMath.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama3.1-8B-PlumMath.Q4_1.gguf	Q4_1	4.78GB
Llama3.1-8B-PlumMath.Q5_0.gguf	Q5_0	5.21GB
Llama3.1-8B-PlumMath.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama3.1-8B-PlumMath.Q5_K.gguf	Q5_K	5.34GB
Llama3.1-8B-PlumMath.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama3.1-8B-PlumMath.Q5_1.gguf	Q5_1	5.65GB
Llama3.1-8B-PlumMath.Q6_K.gguf	Q6_K	6.14GB
Llama3.1-8B-PlumMath.Q8_0.gguf	Q8_0	7.95GB

Original model description:

language:

en license: llama3.1 library_name: transformers tags:
mergekit
merge
shining-valiant
shining-valiant-2
cobalt
plum
valiant
valiant-labs
llama
llama-3.1
llama-3.1-instruct
llama-3.1-instruct-8b
llama-3
llama-3-instruct
llama-3-instruct-8b
8b
math
math-instruct
science
physics
biology
chemistry
compsci
computer-science
engineering
technical
conversational
chat
instruct base_model:
meta-llama/Llama-3.1-8B-Instruct
ValiantLabs/Llama3.1-8B-ShiningValiant2
ValiantLabs/Llama3.1-8B-Cobalt pipeline_tag: text-generation model_type: llama model-index:
name: sequelbox/Llama3.1-8B-PlumMath results:
- task: type: text-generation name: Text Generation dataset: name: Winogrande (5-Shot) type: Winogrande args: num_few_shot: 5 metrics:
  - type: acc value: 72.38 name: acc
- task: type: text-generation name: Text Generation dataset: name: MathQA (5-Shot) type: MathQA args: num_few_shot: 5 metrics:
  - type: acc value: 40.27 name: acc
- task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics:
  - type: inst_level_strict_acc and prompt_level_strict_acc value: 22.42 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics:
  - type: acc_norm value: 16.45 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics:
  - type: exact_match value: 3.93 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics:
  - type: acc_norm value: 9.06 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics:
  - type: acc_norm value: 8.98 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 21.95 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath name: Open LLM Leaderboard

PlumMath

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

Merge Details

Merge Method

This model was merged using the della merge method using meta-llama/Llama-3.1-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: della
dtype: bfloat16
parameters:
  normalize: true
models:
  - model: ValiantLabs/Llama3.1-8B-ShiningValiant2
    parameters:
      density: 0.5
      weight: 0.3
  - model: ValiantLabs/Llama3.1-8B-Cobalt
    parameters:
      density: 0.5
      weight: 0.2
base_model: meta-llama/Llama-3.1-8B-Instruct

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	13.80
IFEval (0-Shot)	22.42
BBH (3-Shot)	16.45
MATH Lvl 5 (4-Shot)	3.93
GPQA (0-shot)	9.06
MuSR (0-shot)	8.98
MMLU-PRO (5-shot)	21.95

RichardErkhov/sequelbox_-_Llama3.1-8B-PlumMath-gguf