RichardErkhov/OEvortex_-_HelpingAI-110M-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

HelpingAI-110M - GGUF

• Model creator: https://huggingface.co/OEvortex/
• Original model: https://huggingface.co/OEvortex/HelpingAI-110M/

Name	Quant method	Size
HelpingAI-110M.Q2_K.gguf	Q2_K	0.05GB
HelpingAI-110M.IQ3_XS.gguf	IQ3_XS	0.05GB
HelpingAI-110M.IQ3_S.gguf	IQ3_S	0.05GB
HelpingAI-110M.Q3_K_S.gguf	Q3_K_S	0.05GB
HelpingAI-110M.IQ3_M.gguf	IQ3_M	0.06GB
HelpingAI-110M.Q3_K.gguf	Q3_K	0.06GB
HelpingAI-110M.Q3_K_M.gguf	Q3_K_M	0.06GB
HelpingAI-110M.Q3_K_L.gguf	Q3_K_L	0.06GB
HelpingAI-110M.IQ4_XS.gguf	IQ4_XS	0.06GB
HelpingAI-110M.Q4_0.gguf	Q4_0	0.06GB
HelpingAI-110M.IQ4_NL.gguf	IQ4_NL	0.06GB
HelpingAI-110M.Q4_K_S.gguf	Q4_K_S	0.06GB
HelpingAI-110M.Q4_K.gguf	Q4_K	0.07GB
HelpingAI-110M.Q4_K_M.gguf	Q4_K_M	0.07GB
HelpingAI-110M.Q4_1.gguf	Q4_1	0.07GB
HelpingAI-110M.Q5_0.gguf	Q5_0	0.07GB
HelpingAI-110M.Q5_K_S.gguf	Q5_K_S	0.07GB
HelpingAI-110M.Q5_K.gguf	Q5_K	0.08GB
HelpingAI-110M.Q5_K_M.gguf	Q5_K_M	0.08GB
HelpingAI-110M.Q5_1.gguf	Q5_1	0.08GB
HelpingAI-110M.Q6_K.gguf	Q6_K	0.08GB
HelpingAI-110M.Q8_0.gguf	Q8_0	0.11GB

Original model description:

language: - en license: other library_name: transformers tags: - Text-Generation - Transformers - HelpingAI datasets: - OEvortex/vortex-mini metrics: - speed license_name: hsul license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md model-index: - name: HelpingAI-110M 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: 22.78 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/HelpingAI-110M 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: 28.02 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/HelpingAI-110M 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: 23.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/HelpingAI-110M 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: 48.25 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/HelpingAI-110M 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: 51.62 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/HelpingAI-110M 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: 0.0 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/HelpingAI-110M name: Open LLM Leaderboard

🌟 HelpingAI-110M Model Card 🌟

📊 Datasets used:

• OEvortex/vortex-mini

🗣️ Language:

• English (en)

🔒 License:

HelpingAI Simplified Universal License (HSUL)

🧠 Model Overview: HelpingAI-110M is a very lite version of the HelpingAI model, trained on a 110M parameters.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.05
AI2 Reasoning Challenge (25-Shot)	22.78
HellaSwag (10-Shot)	28.02
MMLU (5-Shot)	23.66
TruthfulQA (0-shot)	48.25
Winogrande (5-shot)	51.62
GSM8k (5-shot)	0.00