Autotrain compatible Dataset:intel/orca dpo pairs En Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mncai/mistral-7b-dpo-v6
Mistral 7B DPO V6 Benchmarks
ARC: 72.53 vs 96.7 (so35)-25%
HellaSwag: 88.1 vs 95.3 (gpt4)-7.6%
MMLU: 64.68 vs 88.3 (so35)-26.7%
TruthfulQA: 68.24 vs 59 (gpt4)15.7%
WinoGrande: 82.56 vs 87.5 (gpt4)-5.6%
GSM8K: 70.89 vs 96.4 (so35)-26.5%
LLME Score: 0.18724
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)
Mistral 7B DPO V6 Parameters and Internals
| Additional Notes | ||
| Supported Languages |
|
| LLM Name | Mistral 7B DPO V6 |
| Repository 🤗 | https://huggingface.co/mncai/mistral-7b-dpo-v6 |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2024-12-26 |
| Maintainer | mncai |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mistral 7B DPO V6
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Nemo Instruct 2407 Abliterated | 1000K / 24.5 GB | 2594 | 9 |
| MegaBeam Mistral 7B 512K | 512K / 14.4 GB | 6791 | 46 |
| SpydazWeb AI HumanAI RP | 512K / 14.4 GB | 31 | 1 |
| SpydazWeb AI HumanAI 002 | 512K / 14.4 GB | 20 | 1 |
| ...daz Web AI ChatML 512K Project | 512K / 14.5 GB | 12 | 0 |
| MegaBeam Mistral 7B 300K | 282K / 14.4 GB | 3252 | 15 |
| Hebrew Mistral 7B 200K | 256K / 30 GB | 3043 | 15 |
| Astral 256K 7B V2 | 250K / 14.4 GB | 18 | 0 |
| Astral 256K 7B | 250K / 14.4 GB | 16 | 0 |
| Boptruth Agatha 7B | 128K / 14.4 GB | 475 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mncai/mistral-7b-dpo-v6 .
Rank the Mistral 7B DPO V6 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? 40248 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217