Firefly Bloom 7b1 Benchmarks
ARC: 40.44-58%
HellaSwag: 61.2-35.8%
MMLU: 26.83-69%
TruthfulQA: 40.83-30.8%
WinoGrande: 64.56-26.2%
GSM8K: 0.68-99.3%
nn.n% — How the model compares to the GPT-4.
Firefly Bloom 7b1 Parameters and Internals
| LLM Name | Firefly Bloom 7b1 |
| Repository | Open on 🤗 |
| Merged Model | Yes |
| Required VRAM | 16.2 GB |
| Updated | 2024-07-27 |
| Maintainer | YeungNLP |
| Model Type | bloom |
| Model Files | |
| Model Architecture | BloomForCausalLM |
| Transformers Version | 4.30.0.dev0 |
| Tokenizer Class | BloomTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 250880 |
| Torch Data Type | float16 |
Best Alternatives to Firefly Bloom 7b1
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...ft Fpft Multilingual Bloom 7b1 | 0.2 | 0K / 28.2 GB | 8 | 1 |
| Simple Finnish Gpt3 Xl | 0.2 | 0K / 0 GB | 30 | 1 |
| Firefly Bloom 2b6 V2 | 0.2 | 0K / 5 GB | 959 | 9 |
| Tiny Random BloomForCausalLM | 0.2 | 0K / 0 GB | 5305 | 0 |
| Bloom Small 166 | 0.2 | 0K / 0.7 GB | 28 | 2 |
| Bloom 1b1 RLHF V2 | 0.2 | 0K / 2.1 GB | 936 | 0 |
| Bloom 1b7 With Lm Head | 0.2 | 0K / 3.4 GB | 3840 | 0 |
| ClinicalGPT Base Zh | 0.2 | 0K / 15.8 GB | 2883 | 23 |
| PULSE 7bv5 | 0.1 | 0K / 16.2 GB | 169 | 29 |
| DElefant | 0.1 | 0K / 12.5 GB | 10 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than YeungNLP/firefly-bloom-7b1 .
Rank the Firefly Bloom 7b1 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