Merged Model Autotrain compatible Base model:mlabonne/alphamonar... Base model:mlabonne/neuralmona... Conversational Endpoints compatible Lora Mistral Mlabonne/alphamonarch-7b Mlabonne/neuralmonarch-7b Model-index Region:us Safetensors Sharded Tensorflow
NeuralMaxime 7B Slerp Benchmarks
ARC: 73.38 vs 96.7 (so35)-24.1%
HellaSwag: 89.18 vs 95.3 (gpt4)-6.4%
MMLU: 64.44 vs 88.3 (so35)-27%
TruthfulQA: 77.79 vs 59 (gpt4)31.8%
WinoGrande: 84.45 vs 87.5 (gpt4)-3.5%
GSM8K: 67.78 vs 96.4 (so35)-29.7%
LLME Score: 0.20349
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)
NeuralMaxime 7B Slerp Parameters and Internals
| LLM Name | NeuralMaxime 7B Slerp |
| Repository 🤗 | https://huggingface.co/Kukedlc/NeuralMaxime-7B-slerp |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2024-09-16 |
| Maintainer | Kukedlc |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 8192 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | model.layers.31.mlp.gate_proj|model.layers.31.self_attn.o_proj|model.layers.31.mlp.up_proj|model.layers.31.self_attn.k_proj|model.layers.31.self_attn.q_proj|model.layers.31.self_attn.v_proj|model.layers.31.mlp.down_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 8 |
Best Alternatives to NeuralMaxime 7B Slerp
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 622354 | 967 |
| Mistral 7B V0.3 | 32K / 14.5 GB | 6854 | 5 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 4444 | 3 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 2151 | 2 |
| ...unoichi Lemon Royale V3 32K 7B | 32K / 14.5 GB | 8 | 4 |
| Mistralai Mistral 7B V0.3 | 32K / 14.5 GB | 2 | 3 |
| ...ralai Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 6 | 1 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 5 | 0 |
| Mistral 7B V0.2 | 32K / 14.5 GB | 78 | 1 |
| Full V4 Astromistral Final | 32K / 4.5 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Kukedlc/NeuralMaxime-7B-slerp .
Rank the NeuralMaxime 7B Slerp 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