Galactica 6.7B Parameters and Internals
| LLM Name | Galactica 6.7B |
| Repository | Open on 🤗 |
| Model Size | 6.7b |
| Required VRAM | 13.8 GB |
| Updated | 2024-07-26 |
| Maintainer | |
| Model Type | opt |
| Model Files | |
| Model Architecture | OPTForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.21.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 50000 |
| Torch Data Type | float16 |
| Activation Function | gelu |
Best Alternatives to Galactica 6.7B
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ....7B Qcqa Ub 16 Best For Q Loss | 0.3 | 2K / 27.4 GB | 311 | 0 |
| ...B Qcqa Ub 16 Best For KV Cache | 0.3 | 2K / 27.4 GB | 317 | 0 |
| Galactica 6.7B ReFT GSM8k | 0.3 | 2K / 13.8 GB | 310 | 0 |
| ...7B Gqa Ub 16 Best For KV Cache | 0.3 | 2K / 27.4 GB | 310 | 0 |
| Galactica 6.7B EssayWriter | 0.2 | 2K / 13.4 GB | 966 | 3 |
| Opt Flan Iml 6.7B | 0.2 | 2K / 26.6 GB | 957 | 1 |
| ...lactica 6.7B Evol Instruct 70K | 0.2 | 2K / 27.4 GB | 941 | 19 |
| OPT 6.7B Nerybus Mix | 0.2 | 2K / 13.7 GB | 1713 | 20 |
| OPT 6.7B Erebus | 0.2 | 2K / 13.3 GB | 30677 | 94 |
| Galactica 6.7B Finetuned | 0.1 | 2K / 27.4 GB | 939 | 34 |
Note: green Score (e.g. "73.2") means that the model is better than facebook/galactica-6.7b .
Rank the Galactica 6.7B 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501