Autotrain compatible Base model:corianas/neural-mis... Base model:merge:corianas/neur... Base model:merge:mistralai/mis... Base model:mistralai/mistral-7... Conversational Corianas/neural-mistral-7b Endpoints compatible Frankenmoe Instruct Lazymergekit Merge Mergekit Mistralai/mistral-7b-instruct-... Mixtral Moe Region:us Safetensors Sharded Tensorflow
NearalMistral 2x7B Benchmarks
ARC: 57.42 vs 96.7 (so35)-40.6%
HellaSwag: 77.67 vs 95.3 (gpt4)-18.5%
MMLU: 56.46 vs 88.3 (so35)-36.1%
TruthfulQA: 57.03 vs 59 (gpt4)-3.3%
WinoGrande: 75.22 vs 87.5 (gpt4)-14%
GSM8K: 31.61 vs 96.4 (so35)-67.2%
LLME Score: 0.22281
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)
NearalMistral 2x7B Parameters and Internals
| LLM Name | NearalMistral 2x7B |
| Repository 🤗 | https://huggingface.co/Corianas/NearalMistral-2x7B |
| Base Model(s) | |
| Model Size | 12.9b |
| Required VRAM | 25.8 GB |
| Updated | 2024-09-16 |
| Maintainer | Corianas |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| 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 NearalMistral 2x7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MergedExpert 2x8b | 32K / 25.8 GB | 5 | 0 |
| MergedExperts 2x8b | 32K / 25.8 GB | 5 | 0 |
| Megatron V3 2x7B | 32K / 25.8 GB | 59 | 3 |
| MistarlingMaid 2x7B Base | 32K / 25.8 GB | 57 | 0 |
| ...afted Hermetic Platypus C 2x7B | 32K / 25.8 GB | 57 | 0 |
| ...tral 7B Instruct V0.2 2x7B MoE | 32K / 25.8 GB | 1131 | 4 |
| Orthogonal 2x7B Base | 32K / 25.8 GB | 652 | 0 |
| Mistral 2x7b V0.1 | 32K / 25.8 GB | 3 | 1 |
| Mistral Math 2x7b Mix | 32K / 25.8 GB | 60 | 4 |
| ...tral Instruct MoE Experimental | 32K / 25.8 GB | 63 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than Corianas/NearalMistral-2x7B .
Rank the NearalMistral 2x7B 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? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803