You can deploy this model and start earning money today!

RichardErkhov/
rmdhirr_-_Gluon-8B-gguf

Name: rmdhirr_-_Gluon-8B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Gluon-8B - GGUF

Model creator: https://huggingface.co/rmdhirr/
Original model: https://huggingface.co/rmdhirr/Gluon-8B/

Name	Quant method	Size
Gluon-8B.Q2_K.gguf	Q2_K	2.96GB
Gluon-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Gluon-8B.IQ3_S.gguf	IQ3_S	3.43GB
Gluon-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Gluon-8B.IQ3_M.gguf	IQ3_M	3.52GB
Gluon-8B.Q3_K.gguf	Q3_K	3.74GB
Gluon-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Gluon-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Gluon-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Gluon-8B.Q4_0.gguf	Q4_0	4.34GB
Gluon-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Gluon-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Gluon-8B.Q4_K.gguf	Q4_K	4.58GB
Gluon-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Gluon-8B.Q4_1.gguf	Q4_1	4.78GB
Gluon-8B.Q5_0.gguf	Q5_0	5.21GB
Gluon-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Gluon-8B.Q5_K.gguf	Q5_K	5.34GB
Gluon-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Gluon-8B.Q5_1.gguf	Q5_1	5.65GB
Gluon-8B.Q6_K.gguf	Q6_K	6.14GB
Gluon-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: apache-2.0 library_name: transformers tags:

mergekit
merge
roleplay
llama
llama-3.1 base_model:
NeverSleep/Lumimaid-v0.2-8B
kloodia/lora-8b-medic
nothingiisreal/L3.1-8B-Celeste-V1.5
kloodia/lora-8b-bio
mlabonne/Hermes-3-Llama-3.1-8B-lorablated
Azazelle/RP_Format_QuoteAsterisk_Llama3
vicgalle/Configurable-Llama-3.1-8B-Instruct
kloodia/lora-8b-physic
Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 model-index:
name: Gluon-8B results:
- 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: 50.53 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-8B 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: 30.34 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-8B 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: 12.54 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-8B 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: 8.28 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-8B 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: 9.09 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-8B 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: 31.2 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-8B name: Open LLM Leaderboard

⚛️ Gluon-8B

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

Quantizations

GGUF

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated+Azazelle/RP_Format_QuoteAsterisk_Llama3
  - model: vicgalle/Configurable-Llama-3.1-8B-Instruct+kloodia/lora-8b-physic
  - model: NeverSleep/Lumimaid-v0.2-8B+kloodia/lora-8b-medic
  - model: nothingiisreal/L3.1-8B-Celeste-V1.5+kloodia/lora-8b-bio
merge_method: model_stock
base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
normalize: true
int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	23.66
IFEval (0-Shot)	50.53
BBH (3-Shot)	30.34
MATH Lvl 5 (4-Shot)	12.54
GPQA (0-shot)	8.28
MuSR (0-shot)	9.09
MMLU-PRO (5-shot)	31.20

RichardErkhov/rmdhirr_-_Gluon-8B-gguf