4bit Autotrain compatible Conversational Endpoints compatible Mistral Quantized Region:us Safetensors Sharded Tensorflow
Zephyr Sft Bnb 4bit DPO Mtbc 213steps Benchmarks
MMLU Pro: 18.98
GPQA: 1.57
MUSR: 9.58
BBH: 19.67
IFEval: 42.75 vs 88 (so35)-51.4%
MATH Lvl 5: 2.04
LLME Score: 0.30687
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)
Zephyr Sft Bnb 4bit DPO Mtbc 213steps Parameters and Internals
| LLM Name | Zephyr Sft Bnb 4bit DPO Mtbc 213steps |
| Repository 🤗 | https://huggingface.co/sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbc-213steps |
| Model Size | 7.2b |
| Required VRAM | 14.4 GB |
| Updated | 2024-10-18 |
| Maintainer | sonthenguyen |
| Model Type | mistral |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.45.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Zephyr Sft Bnb 4bit DPO Mtbc 213steps
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Sft Bnb 4bit DPO Mtbo 180steps | 32K / 14.4 GB | 53 | 0 |
| ...Sft Bnb 4bit DPO Mtbr 180steps | 32K / 14.4 GB | 23 | 0 |
| Zephyr DPO V2 | 32K / 14.4 GB | 1340 | 1 |
| AI Tutor | 32K / 14.5 GB | 9 | 0 |
| Rezephyr DPO | 32K / 14.4 GB | 7 | 0 |
| ...zWeb AI LCARS Humanization 001 | 512K / 14.4 GB | 64 | 2 |
| ...zWeb AI LCARS Humanization 003 | 512K / GB | 48 | 0 |
| SpydazWeb AI HumanAI 001 | 512K / GB | 0 | 1 |
| Spydaz Web AI BIBLE 002 | 512K / 14.4 GB | 11 | 2 |
| SpydazWeb HumanAI M2 | 512K / GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbc-213steps .
Rank the Zephyr Sft Bnb 4bit DPO Mtbc 213steps 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803