8-bit 8bit Autotrain compatible Bitsandbytes Endpoints compatible Opt Quantized Region:us Safetensors
Fbopt 350M 8bit Benchmarks
ARC: 23.55-75.5%
HellaSwag: 36.6-61.6%
MMLU: 26.22-69.7%
TruthfulQA: 40.97-30.6%
WinoGrande: 52.64-39.8%
GSM8K: 1.29-98.6%
nn.n% — How the model compares to the GPT-4.
Fbopt 350M 8bit Parameters and Internals
| LLM Name | Fbopt 350M 8bit |
| Repository | Open on 🤗 |
| Model Size | 350m |
| Required VRAM | 0.4 GB |
| Updated | 2024-07-27 |
| Maintainer | yec019 |
| Model Type | opt |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | OPTForCausalLM |
| License | unknown |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.36.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 50272 |
| Torch Data Type | float16 |
| Activation Function | relu |
| Errors | replace |
Best Alternatives to Fbopt 350M 8bit
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Ov Opt 350M 8bit Kv Cache | 0.1 | 2K / 0.4 GB | 11 | 1 |
| Opt Mini Dataset 0 | 0.2 | 2K / 0.7 GB | 14 | 0 |
| Facebook Opt 350M SFT Korz14 | 0.2 | 2K / 0.7 GB | 22 | 0 |
| Temp Model Sft | 0.2 | 2K / 1.3 GB | 6 | 0 |
| Gpt350 Chat S V0 1 | 0.2 | 2K / 0.7 GB | 67 | 0 |
| Gpt350 Chat S V0 | 0.2 | 2K / 0.7 GB | 36 | 0 |
| Dadjokes Tuned Opt | 0.2 | 2K / 1.3 GB | 11 | 2 |
| Sunday | 0.2 | 2K / 1.3 GB | 10 | 0 |
| Rockyalquimista888 | 0.2 | 2K / 1.3 GB | 8 | 0 |
| Remedycure | 0.2 | 2K / 1.3 GB | 7 | 0 |
Rank the Fbopt 350M 8bit 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501