Alignment-handbook Autotrain compatible Base model:finetune:shenaozhan... Base model:shenaozhang/0.001 i... Conversational Dataset:shenaozhang/0.001 idpo... Dpo Endpoints compatible Generated from trainer Mistral Region:us Safetensors Sharded Tensorflow Trl
0.001 Idpo Iter 3 Benchmarks
ARC: 63.74 vs 96.7 (so35)-34.1%
HellaSwag: 85.58 vs 95.3 (gpt4)-10.2%
MMLU: 60.33 vs 88.3 (so35)-31.7%
TruthfulQA: 55.48 vs 59 (gpt4)-6%
WinoGrande: 77.82 vs 87.5 (gpt4)-11.1%
GSM8K: 32.75 vs 96.4 (so35)-66%
LLME Score: 0.22313
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)
0.001 Idpo Iter 3 Parameters and Internals
| LLM Name | 0.001 Idpo Iter 3 |
| Repository 🤗 | https://huggingface.co/ShenaoZhang/0.001_idpo_iter_3 |
| Base Model(s) | |
| Model Size | 7.2b |
| Required VRAM | 14.4 GB |
| Updated | 2024-09-20 |
| Maintainer | ShenaoZhang |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to 0.001 Idpo Iter 3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Spydaz Web AI BIBLE 002 | 512K / 14.4 GB | 26 | 0 |
| Spydaz Web AI 08 | 512K / 14.5 GB | 76 | 1 |
| Spydaz Web AI ChatML 002 | 512K / 14.4 GB | 24 | 0 |
| Spydaz Web AI ChatQA 001 UFT | 512K / 14.4 GB | 32 | 1 |
| Spydaz Web AI ChatQA 001 SFT | 512K / 14.4 GB | 23 | 1 |
| Spydaz Web AI ChatQA 001 | 512K / 14.4 GB | 17 | 1 |
| Spydaz Web AI BIBLE 001 | 512K / 14.4 GB | 14 | 0 |
| Spydaz Web AI 010 | 512K / 14.5 GB | 14 | 0 |
| Openchat 3.5 0106 128K DPO | 128K / 14.4 GB | 65 | 2 |
| Mistral7B PairRM SPPO Iter2 | 32K / 14.4 GB | 4914 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than ShenaoZhang/0.001_idpo_iter_3 .
Rank the 0.001 Idpo Iter 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? 36073 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803