RichardErkhov/ResplendentAI_-_Flora_7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Flora_7B - GGUF

• Model creator: https://huggingface.co/ResplendentAI/
• Original model: https://huggingface.co/ResplendentAI/Flora_7B/

Name	Quant method	Size
Flora_7B.Q2_K.gguf	Q2_K	2.53GB
Flora_7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Flora_7B.IQ3_S.gguf	IQ3_S	2.96GB
Flora_7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Flora_7B.IQ3_M.gguf	IQ3_M	3.06GB
Flora_7B.Q3_K.gguf	Q3_K	3.28GB
Flora_7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Flora_7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Flora_7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Flora_7B.Q4_0.gguf	Q4_0	3.83GB
Flora_7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Flora_7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Flora_7B.Q4_K.gguf	Q4_K	4.07GB
Flora_7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Flora_7B.Q4_1.gguf	Q4_1	4.24GB
Flora_7B.Q5_0.gguf	Q5_0	4.65GB
Flora_7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Flora_7B.Q5_K.gguf	Q5_K	4.78GB
Flora_7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Flora_7B.Q5_1.gguf	Q5_1	5.07GB
Flora_7B.Q6_K.gguf	Q6_K	5.53GB
Flora_7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

language: - en license: cc-by-sa-4.0 library_name: transformers tags: - finetune base_model: - jeiku/FloraBase - jeiku/Synthetic_Soul_1k_Mistral_128 datasets: - ResplendentAI/Synthetic_Soul_1k model-index: - name: Flora_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: 72.1 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 88.31 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 64.16 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 71.19 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 84.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 65.35 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_7B name: Open LLM Leaderboard

Flora

Quants available here:

https://huggingface.co/bartowski/Flora_7B-GGUF

https://huggingface.co/bartowski/Flora_7B-exl2

https://huggingface.co/solidrust/Flora-7B-AWQ

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
models:
  - model: jeiku/FloraBase+jeiku/Synthetic_Soul_1k_Mistral_128
    parameters:
      weight: 1       
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.26
AI2 Reasoning Challenge (25-Shot)	72.10
HellaSwag (10-Shot)	88.31
MMLU (5-Shot)	64.16
TruthfulQA (0-shot)	71.19
Winogrande (5-shot)	84.45
GSM8k (5-shot)	65.35