Autotrain compatible Base model:finetune:liminerity... Base model:liminerity/bitnet-m... Endpoints compatible Frankenmoe Lazymergekit Liminerity/bitnet-m7-70m Merge Mergekit Mixtral Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/liminerity/m7-1.58bit-6x70m
M7 1.58bit 6x70m Benchmarks
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)
M7 1.58bit 6x70m Parameters and Internals
| Model Type |
|
| LLM Name | M7 1.58bit 6x70m |
| Repository 🤗 | https://huggingface.co/liminerity/m7-1.58bit-6x70m |
| Base Model(s) | |
| Model Size | 134.1m |
| Required VRAM | 0.5 GB |
| Updated | 2025-02-22 |
| Maintainer | liminerity |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 768 |
| Model Max Length | 768 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Rank the M7 1.58bit 6x70m 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227