You can deploy this model and start earning money today!

RichardErkhov/
ehristoforu_-_SoRu-0009-gguf

Name: ehristoforu_-_SoRu-0009-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SoRu-0009 - GGUF

Model creator: https://huggingface.co/ehristoforu/
Original model: https://huggingface.co/ehristoforu/SoRu-0009/

Name	Quant method	Size
SoRu-0009.Q2_K.gguf	Q2_K	0.32GB
SoRu-0009.IQ3_XS.gguf	IQ3_XS	0.32GB
SoRu-0009.IQ3_S.gguf	IQ3_S	0.32GB
SoRu-0009.Q3_K_S.gguf	Q3_K_S	0.31GB
SoRu-0009.IQ3_M.gguf	IQ3_M	0.32GB
SoRu-0009.Q3_K.gguf	Q3_K	0.33GB
SoRu-0009.Q3_K_M.gguf	Q3_K_M	0.33GB
SoRu-0009.Q3_K_L.gguf	Q3_K_L	0.34GB
SoRu-0009.IQ4_XS.gguf	IQ4_XS	0.33GB
SoRu-0009.Q4_0.gguf	Q4_0	0.33GB
SoRu-0009.IQ4_NL.gguf	IQ4_NL	0.33GB
SoRu-0009.Q4_K_S.gguf	Q4_K_S	0.36GB
SoRu-0009.Q4_K.gguf	Q4_K	0.37GB
SoRu-0009.Q4_K_M.gguf	Q4_K_M	0.37GB
SoRu-0009.Q4_1.gguf	Q4_1	0.35GB
SoRu-0009.Q5_0.gguf	Q5_0	0.37GB
SoRu-0009.Q5_K_S.gguf	Q5_K_S	0.38GB
SoRu-0009.Q5_K.gguf	Q5_K	0.39GB
SoRu-0009.Q5_K_M.gguf	Q5_K_M	0.39GB
SoRu-0009.Q5_1.gguf	Q5_1	0.39GB
SoRu-0009.Q6_K.gguf	Q6_K	0.47GB
SoRu-0009.Q8_0.gguf	Q8_0	0.49GB

Original model description:

language:

en license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
qwen2
trl
sft base_model: ehristoforu/SoRu-0008 model-index:
name: SoRu-0009 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: 25.82 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/SoRu-0009 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: 5.14 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/SoRu-0009 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: 0.0 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/SoRu-0009 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: 1.45 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/SoRu-0009 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: 0.62 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/SoRu-0009 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: 2.66 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/SoRu-0009 name: Open LLM Leaderboard

Uploaded model

Developed by: ehristoforu
License: apache-2.0
Finetuned from model : ehristoforu/SoRu-0008

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	5.95
IFEval (0-Shot)	25.82
BBH (3-Shot)	5.14
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	1.45
MuSR (0-shot)	0.62
MMLU-PRO (5-shot)	2.66

RichardErkhov/ehristoforu_-_SoRu-0009-gguf

Original model description:

Uploaded model

Open LLM Leaderboard Evaluation Results

RichardErkhov/
ehristoforu_-_SoRu-0009-gguf