Autotrain compatible Base model:kukedlc/neuralsynth... Base model:merge:kukedlc/neura... Base model:merge:mistralai/mis... Base model:merge:mlabonne/alph... Base model:merge:s3nh/severusw... Base model:mistralai/mistral-7... Base model:mlabonne/alphamonar... Base model:s3nh/severuswestlak... Conversational Endpoints compatible Frankenmoe Instruct Kukedlc/neuralsynthesis-7b-v0.... Lazymergekit Merge Mergekit Mistralai/mistral-7b-instruct-... Mixtral Mlabonne/alphamonarch-7b Moe Region:us S3nh/severuswestlake-7b-dpo Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/jsfs11/MixtureofMerges-MoE-4x7b-v10-mixtralv0.3
MixtureofMerges MoE 4x7b V10 Mixtralv0.3 Benchmarks
ARC: 66.38 vs 96.7 (so35)-31.4%
HellaSwag: 84.9 vs 95.3 (gpt4)-10.9%
MMLU: 63.38 vs 88.3 (so35)-28.2%
TruthfulQA: 56.83 vs 59 (gpt4)-3.7%
WinoGrande: 80.98 vs 87.5 (gpt4)-7.5%
GSM8K: 57.54 vs 96.4 (so35)-40.3%
LLME Score: 0.20337
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)
MixtureofMerges MoE 4x7b V10 Mixtralv0.3 Parameters and Internals
| Model Type |
|
| LLM Name | MixtureofMerges MoE 4x7b V10 Mixtralv0.3 |
| Repository 🤗 | https://huggingface.co/jsfs11/MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 |
| Base Model(s) | |
| Model Size | 24.2b |
| Required VRAM | 48.3 GB |
| Updated | 2025-02-05 |
| Maintainer | jsfs11 |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32768 |
| Torch Data Type | bfloat16 |
Best Alternatives to MixtureofMerges MoE 4x7b V10 Mixtralv0.3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Proto Athena 4x7B | 32K / 48.4 GB | 8 | 0 |
| Proto Athena V0.2 4x7B | 32K / 48.4 GB | 5 | 0 |
| MoE Merging | 32K / 48.3 GB | 1214 | 0 |
| Sixtyoneeighty 4x7B V1 | 32K / 48.3 GB | 52 | 0 |
| MixtureofMerges MoE 4x7bRP V11 | 32K / 48.3 GB | 8 | 1 |
| ...icon Mixtral87 Merged Torch212 | 32K / 26.7 GB | 5 | 0 |
| Eclipse Mistral 4x7b | 32K / 48.5 GB | 16 | 1 |
| Kicon Mixtral87 Merged 41766 | 32K / 26.7 GB | 5 | 0 |
| Boundary Mistral 4x7b MoE | 32K / 48.7 GB | 117 | 1 |
| ...x7b Quantized Portuguese Luana | 32K / 26.7 GB | 50 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than jsfs11/MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 .
Rank the MixtureofMerges MoE 4x7b V10 Mixtralv0.3 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227