Firefly Bloom 2b6 V2 Benchmarks
ARC: 27.65 vs 96.7 (so35)-71.4%
HellaSwag: 39.23 vs 95.3 (gpt4)-58.8%
MMLU: 25.24 vs 88.3 (so35)-71.4%
TruthfulQA: 42.27 vs 59 (gpt4)-28.4%
WinoGrande: 54.78 vs 87.5 (gpt4)-37.4%
GSM8K: 1.74 vs 96.4 (so35)-98.2%
LLME Score: 0.1735
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)
Firefly Bloom 2b6 V2 Parameters and Internals
| LLM Name | Firefly Bloom 2b6 V2 |
| Repository 🤗 | https://huggingface.co/YeungNLP/firefly-bloom-2b6-v2 |
| Required VRAM | 5 GB |
| Updated | 2024-09-07 |
| Maintainer | YeungNLP |
| Model Type | bloom |
| Model Files | |
| Model Architecture | BloomForCausalLM |
| Transformers Version | 4.29.0.dev0 |
| Tokenizer Class | BloomTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 46145 |
| Torch Data Type | float16 |
Best Alternatives to Firefly Bloom 2b6 V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bigscience Bloomz 7b1 4bits | 0K / 5.5 GB | 7 | 0 |
| ...ft Fpft Multilingual Bloom 7b1 | 0K / 28.2 GB | 3 | 1 |
| Tiny Random BloomForCausalLM | 0K / 0 GB | 14206 | 0 |
| Firefly Bloom 7b1 | 0K / 16.2 GB | 675 | 1 |
| Simple Finnish Gpt3 Xl | 0K / 0 GB | 17 | 1 |
| Bloom Small 166 | 0K / 0.7 GB | 9 | 2 |
| ...BloomForCausalLM Correct Vocab | 0K / 0 GB | 91935 | 0 |
| Bloom 1b7 With Lm Head | 0K / 3.4 GB | 4386 | 0 |
| ClinicalGPT Base Zh | 0K / 15.8 GB | 2779 | 34 |
| Bloom 1b1 RLHF V2 | 0K / 2.1 GB | 718 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than YeungNLP/firefly-bloom-2b6-v2 .
Rank the Firefly Bloom 2b6 V2 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803