Arxiv:2210.17323 4-bit 4bit Ak Ar As Autotrain compatible Base model:bigscience/bloom-1b... Base model:quantized:bigscienc... Bloom Bm Bn Ca Code En Es Eu Fon Fr Gptq Gu Hi Id Ig Ki Kn Lg Ln Ml Mr Ne Nso Ny Or Pa Pt Quantized Region:us Rn Rw Safetensors Sn St Sw Ta Te Tn Ts Tum Tw Ur Vi Wo Xh Yo Zh Zhs Zht Zu
Bloom 1b7 GPTQ 4bit G128 Benchmarks
ARC: 30.63 vs 96.7 (so35)-68.3%
HellaSwag: 47.6 vs 95.3 (gpt4)-50.1%
MMLU: 27.48 vs 88.3 (so35)-68.9%
TruthfulQA: 41.31 vs 59 (gpt4)-30%
WinoGrande: 56.04 vs 87.5 (gpt4)-36%
GSM8K: 0.83 vs 96.4 (so35)-99.1%
LLME Score: 0.21356
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)
Bloom 1b7 GPTQ 4bit G128 Parameters and Internals
| LLM Name | Bloom 1b7 GPTQ 4bit G128 |
| Repository 🤗 | https://huggingface.co/iproskurina/bloom-1b7-GPTQ-4bit-g128 |
| Model Name | bloom-1b7 |
| Model Creator | bigscience |
| Base Model(s) | |
| Model Size | 1.2b |
| Required VRAM | 2.7 GB |
| Updated | 2024-10-11 |
| Maintainer | iproskurina |
| Model Type | bloom |
| Model Files | |
| Supported Languages | ak ar as bm bn ca code en es eu fr gu hi id ig ki kn lg ln ml mr ne ny or pa pt rn rw sn st sw ta te tn ts tw ur vi wo xh yo zh zu |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | BloomForCausalLM |
| License | bigscience-bloom-rail-1.0 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | BloomTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 250880 |
| Torch Data Type | float16 |
Best Alternatives to Bloom 1b7 GPTQ 4bit G128
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bloom 1b7 Gptq 4bit | 0K / 2.7 GB | 12 | 0 |
Rank the Bloom 1b7 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? 36726 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803