Facebook Opt 6.7B Gqa Ub 16 Best For KV Cache Benchmarks
ARC: 23.04 vs 96.7 (so35)-76.2%
HellaSwag: 25.94 vs 95.3 (gpt4)-72.8%
MMLU: 23.12 vs 88.3 (so35)-73.8%
TruthfulQA: 48.99 vs 59 (gpt4)-17%
WinoGrande: 51.93 vs 87.5 (gpt4)-40.7%
LLME Score: 0.2322
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)
Facebook Opt 6.7B Gqa Ub 16 Best For KV Cache Parameters and Internals
| LLM Name | Facebook Opt 6.7B Gqa Ub 16 Best For KV Cache |
| Repository 🤗 | https://huggingface.co/saarvajanik/facebook-opt-6.7b-gqa-ub-16-best-for-KV-cache |
| Model Size | 6.7b |
| Required VRAM | 27.4 GB |
| Updated | 2024-10-17 |
| Maintainer | saarvajanik |
| Model Type | opt |
| Model Files | |
| Supported Languages | en |
| Model Architecture | OPTForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.23.1 |
| Tokenizer Class | GPT2Tokenizer |
| Beginning of Sentence Token | </s> |
| End of Sentence Token | </s> |
| Unk Token | </s> |
| Vocabulary Size | 50272 |
| Torch Data Type | float32 |
| Activation Function | relu |
| Errors | replace |
Best Alternatives to Facebook Opt 6.7B Gqa Ub 16 Best For KV Cache
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ....7B Qcqa Ub 16 Best For Q Loss | 2K / 27.4 GB | 52 | 0 |
| ...B Qcqa Ub 16 Best For KV Cache | 2K / 27.4 GB | 52 | 0 |
| Galactica 6.7B ReFT GSM8k | 2K / 13.8 GB | 50 | 0 |
| Galactica 6.7B EssayWriter | 2K / 13.4 GB | 1111 | 3 |
| Opt Flan Iml 6.7B | 2K / 26.6 GB | 1177 | 1 |
| ...lactica 6.7B Evol Instruct 70K | 2K / 27.4 GB | 1231 | 19 |
| OPT 6.7B Nerybus Mix | 2K / 13.7 GB | 1490 | 20 |
| Galactica 6.7B Finetuned | 2K / 27.4 GB | 1131 | 34 |
| OPI Galactica 6.7B | 2K / 0 GB | 71 | 4 |
| OPI Full Galactica 6.7B | 2K / 27.3 GB | 11 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than saarvajanik/facebook-opt-6.7b-gqa-ub-16-best-for-KV-cache .
Rank the Facebook Opt 6.7B Gqa Ub 16 Best For KV Cache 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803