Arxiv:2210.17323 4-bit 4bit Autotrain compatible Base model:facebook/opt-1.3b Base model:quantized:facebook/... En Gptq Opt Pretrained Quantized Region:us Safetensors
Opt 1.3B GPTQ 4bit G128 Benchmarks
ARC: 29.52 vs 96.7 (so35)-69.5%
HellaSwag: 54.53 vs 95.3 (gpt4)-42.8%
MMLU: 24.96 vs 88.3 (so35)-71.7%
TruthfulQA: 38.71 vs 59 (gpt4)-34.4%
WinoGrande: 59.75 vs 87.5 (gpt4)-31.7%
GSM8K: 0.15 vs 96.4 (so35)-99.8%
LLME Score: 0.21632
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)
Opt 1.3B GPTQ 4bit G128 Parameters and Internals
| LLM Name | Opt 1.3B GPTQ 4bit G128 |
| Repository 🤗 | https://huggingface.co/iproskurina/opt-1.3b-GPTQ-4bit-g128 |
| Model Name | opt-1.3b |
| Model Creator | |
| Base Model(s) | |
| Model Size | 1.3b |
| Required VRAM | 1.1 GB |
| Updated | 2024-10-04 |
| Maintainer | iproskurina |
| Model Type | opt |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | OPTForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 50272 |
| Torch Data Type | float16 |
| Activation Function | relu |
| Errors | replace |
Best Alternatives to Opt 1.3B GPTQ 4bit G128
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Opt 1.3B Gptq 4bit | 2K / 1.1 GB | 7 | 0 |
| ... Distilled PromptKD Dolly V1.0 | 2K / 2.6 GB | 5 | 0 |
| New Galactica 1.3b Mcq | 2K / 2.6 GB | 5 | 0 |
| ... Galactica 1.3b DPO 0.1beta Ai | 2K / 2.6 GB | 3 | 1 |
| New Galactica 1.3b Mcq No Rag | 2K / 2.6 GB | 6 | 0 |
| New Galactica 1.3b Mcq Rag | 2K / 2.6 GB | 6 | 0 |
| ... Galactica 1.3b DPO 0.1beta Ai | 2K / 2.6 GB | 6 | 0 |
| ...tica 1.3b 0.1beta Ai Raft Top3 | 2K / 2.6 GB | 6 | 0 |
| ...tica 1.3b 0.1beta Ai Raft Top4 | 2K / 2.6 GB | 6 | 0 |
| ... Galactica 1.3b DPO 0.1beta Ai | 2K / 2.6 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than iproskurina/opt-1.3b-GPTQ-4bit-g128 .
Rank the Opt 1.3B GPTQ 4bit G128 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? 36542 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803