Alignment-handbook Autotrain compatible Base model:finetune:shenaozhan... Base model:shenaozhang/0.001 z... Conversational Dataset:original Dataset:updated Dpo Endpoints compatible Generated from trainer Mistral Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/ShenaoZhang/0.001_zephyr_5551_4iters_bs256_iter_4
0.001 Zephyr 5551 4iters Bs256 Iter 4 Benchmarks
ARC: 61.18 vs 96.7 (so35)-36.7%
HellaSwag: 85.02 vs 95.3 (gpt4)-10.8%
MMLU: 60.01 vs 88.3 (so35)-32%
TruthfulQA: 52.25 vs 59 (gpt4)-11.4%
WinoGrande: 77.66 vs 87.5 (gpt4)-11.2%
GSM8K: 17.06 vs 96.4 (so35)-82.3%
LLME Score: 0.20575
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 Zephyr 5551 4iters Bs256 Iter 4 Parameters and Internals
| Training Details |
|
| LLM Name | 0.001 Zephyr 5551 4iters Bs256 Iter 4 |
| Repository 🤗 | https://huggingface.co/ShenaoZhang/0.001_zephyr_5551_4iters_bs256_iter_4 |
| Base Model(s) | |
| Model Size | 7.2b |
| Required VRAM | 14.4 GB |
| Updated | 2025-02-17 |
| Maintainer | ShenaoZhang |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to 0.001 Zephyr 5551 4iters Bs256 Iter 4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Web AI HumanAI 012 INSTRUCT XA | 512K / 14.4 GB | 9 | 0 |
| 14 | 512K / 14.5 GB | 319 | 0 |
| ...Web AI HumanAI 012 INSTRUCT IA | 512K / 14.4 GB | 8 | 0 |
| ...Web AI HumanAI 011 INSTRUCT ML | 512K / 14.4 GB | 7 | 0 |
| ...dazWeb AI HumanAI 011 INSTRUCT | 512K / 14.4 GB | 14 | 1 |
| SpydazWeb HumanAI M2 | 512K / GB | 38 | 0 |
| SpydazWeb AI HumanAI 009 CHAT | 512K / 14.4 GB | 6 | 0 |
| SpydazWeb AI HumanAI 007 | 512K / 14.4 GB | 5 | 0 |
| ...Web AI HumanAI 012 INSTRUCT MX | 512K / 14.4 GB | 8 | 0 |
| SpydazWeb AI HumanAI 010 CHAT | 512K / 14.4 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ShenaoZhang/0.001_zephyr_5551_4iters_bs256_iter_4 .
Rank the 0.001 Zephyr 5551 4iters Bs256 Iter 4 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