Arxiv:2304.12244 Alpaca Autotrain compatible Dataset:victor123/evol instruc... Galactica Instruct Opt Pytorch Region:us Sharded Wizardlm
Galactica 6.7B Evol Instruct 70K Benchmarks
ARC: 42.58 vs 96.7 (so35)-56%
HellaSwag: 49.3 vs 95.3 (gpt4)-48.3%
MMLU: 32.96 vs 88.3 (so35)-62.7%
TruthfulQA: 42.1 vs 59 (gpt4)-28.6%
WinoGrande: 56.27 vs 87.5 (gpt4)-35.7%
GSM8K: 0.38 vs 96.4 (so35)-99.6%
LLME Score: 0.1713
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)
Galactica 6.7B Evol Instruct 70K Parameters and Internals
| LLM Name | Galactica 6.7B Evol Instruct 70K |
| Repository 🤗 | https://huggingface.co/GeorgiaTechResearchInstitute/galactica-6.7b-evol-instruct-70k |
| Model Size | 6.7b |
| Required VRAM | 27.4 GB |
| Updated | 2024-09-07 |
| Maintainer | GeorgiaTechResearchInstitute |
| Model Type | opt |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | OPTForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.28.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 50000 |
| Torch Data Type | float32 |
| Activation Function | gelu |
Best Alternatives to Galactica 6.7B Evol Instruct 70K
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Galactica 6.7B EssayWriter | 2K / 13.4 GB | 700 | 3 |
| Opt Flan Iml 6.7B | 2K / 26.6 GB | 711 | 1 |
| Ev Glaive Math1 | 2K / 27.4 GB | 10 | 0 |
| Ev Glaive Math | 2K / 27.4 GB | 7 | 0 |
| Open Instruct Opt 6.7B Tulu | 2K / 26.6 GB | 11 | 2 |
| LongForm OPT 6.7B | 2K / 13.3 GB | 11 | 4 |
| ...PT 6.7B Erebus Instruct Follow | 2K / 13.8 GB | 10 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than GeorgiaTechResearchInstitute/galactica-6.7b-evol-instruct-70k .
Rank the Galactica 6.7B Evol Instruct 70K 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803