Autotrain compatible Base model:finetune:titanml/ti... Base model:titanml/tiny-mixtra... Endpoints compatible Mixtral Moe Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Isaak-Carter/TinyJ.O.S.I.E.-8x220M-base
TinyJ.O.S.I.E. 8x220M Base 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)
TinyJ.O.S.I.E. 8x220M Base Parameters and Internals
| Additional Notes |
|
| LLM Name | TinyJ.O.S.I.E. 8x220M Base |
| Repository 🤗 | https://huggingface.co/Isaak-Carter/TinyJ.O.S.I.E.-8x220M-base |
| Base Model(s) | |
| Model Size | 247m |
| Required VRAM | 0.5 GB |
| Updated | 2024-09-21 |
| Maintainer | Isaak-Carter |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.39.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32024 |
| Torch Data Type | float16 |
Best Alternatives to TinyJ.O.S.I.E. 8x220M Base
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Tiny Mixtral | 128K / 1 GB | 61861 | 1 |
| Mixtral Tiny | 128K / 0.5 GB | 73394 | 10 |
| TinyJ.O.S.I.E. 8x220M Base | 128K / 0.5 GB | 19 | 1 |
| Tiny Mixtral | 128K / 1 GB | 133 | 2 |
| Mixtral Tiny | 1K / 0.5 GB | 1444 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Isaak-Carter/TinyJ.O.S.I.E.-8x220M-base .
Rank the TinyJ.O.S.I.E. 8x220M Base 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