Experiment28 7B Benchmarks
ARC: 73.04 vs 96.7 (so35)-24.5%
HellaSwag: 89.04 vs 95.3 (gpt4)-6.6%
MMLU: 64.44 vs 88.3 (so35)-27%
TruthfulQA: 78.49 vs 59 (gpt4)33%
WinoGrande: 85.4 vs 87.5 (gpt4)-2.4%
GSM8K: 69.29 vs 96.4 (so35)-28.1%
LLME Score: 0.19333
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Experiment28 7B Parameters and Internals
| Model Type |
| |
| Additional Notes | An experiment for testing and refining a specific training and evaluation pipeline research framework. This experiment aims to identify potential optimizations, focusing on data engineering, architecture efficiency, and evaluation performance. The goal is to evaluate the effectiveness of a new training/evaluation pipeline for LLMs. The experiment will explore adjustments in data preprocessing, model training algorithms, and evaluation metrics to test methods for improvement. More details in the future experiments. |
| LLM Name | Experiment28 7B |
| Repository 🤗 | https://huggingface.co/yam-peleg/Experiment28-7B |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2024-11-14 |
| Maintainer | yam-peleg |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Experiment28 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Nemo Instruct 2407 Abliterated | 1000K / 24.5 GB | 2534 | 6 |
| MegaBeam Mistral 7B 512K | 512K / 14.4 GB | 3765 | 41 |
| SpydazWeb AI HumanAI RP | 512K / 14.4 GB | 89 | 1 |
| SpydazWeb AI HumanAI 002 | 512K / 14.4 GB | 56 | 1 |
| ...daz Web AI ChatML 512K Project | 512K / 14.5 GB | 12 | 0 |
| MegaBeam Mistral 7B 300K | 282K / 14.4 GB | 3110 | 15 |
| Hebrew Mistral 7B 200K | 256K / 30 GB | 3218 | 15 |
| Astral 256K 7B | 250K / 14.4 GB | 17 | 0 |
| Astral 256K 7B V2 | 250K / 14.4 GB | 9 | 0 |
| Boptruth Agatha 7B | 128K / 14.4 GB | 653 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than yam-peleg/Experiment28-7B .
Rank the Experiment28 7B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 37960 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110