Merged Model Aurelpx/percival 01-7b-slerp Autotrain compatible Base model:aurelpx/percival 01... Base model:louisbrulenaudet/pe... Conversational Endpoints compatible Louisbrulenaudet/pearl-7b-sler... Mistral Model-index Region:us Safetensors Sharded Tensorflow
StrangeMerges 49 7B Dare Ties Benchmarks
ARC: 72.35 vs 96.7 (so35)-25.2%
HellaSwag: 88.3 vs 95.3 (gpt4)-7.3%
MMLU: 64.31 vs 88.3 (so35)-27.2%
TruthfulQA: 74.7 vs 59 (gpt4)26.6%
WinoGrande: 83.74 vs 87.5 (gpt4)-4.3%
GSM8K: 69.6 vs 96.4 (so35)-27.8%
LLME Score: 0.20149
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)
StrangeMerges 49 7B Dare Ties Parameters and Internals
| Model Type |
| |
| Additional Notes | StrangeMerges_49-7B-dare_ties is a merged model created using LazyMergekit. It is derived from StrangeMerges_32-7B-slerp, AurelPx/Percival_01-7b-slerp, and louisbrulenaudet/Pearl-7B-slerp under specific parameter configurations. |
| LLM Name | StrangeMerges 49 7B Dare Ties |
| Repository 🤗 | https://huggingface.co/Gille/StrangeMerges_49-7B-dare_ties |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2024-11-09 |
| Maintainer | Gille |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to StrangeMerges 49 7B Dare Ties
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Nemo Instruct 2407 Abliterated | 1000K / 24.5 GB | 2600 | 6 |
| MegaBeam Mistral 7B 512K | 512K / 14.4 GB | 4548 | 41 |
| SpydazWeb AI HumanAI RP | 512K / 14.4 GB | 88 | 1 |
| SpydazWeb AI HumanAI 002 | 512K / 14.4 GB | 55 | 1 |
| ...daz Web AI ChatML 512K Project | 512K / 14.5 GB | 12 | 0 |
| MegaBeam Mistral 7B 300K | 282K / 14.4 GB | 3093 | 15 |
| Hebrew Mistral 7B 200K | 256K / 30 GB | 3162 | 15 |
| Astral 256K 7B | 250K / 14.4 GB | 15 | 0 |
| Astral 256K 7B V2 | 250K / 14.4 GB | 8 | 0 |
| Boptruth Agatha 7B | 128K / 14.4 GB | 652 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Gille/StrangeMerges_49-7B-dare_ties .
Rank the StrangeMerges 49 7B Dare Ties 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? 37688 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110