Alignment-handbook Autotrain compatible Base model:finetune:georgiatec... Base model:georgiatech/0.0 lla... Conversational Dataset:original Dataset:updated Dpo Endpoints compatible Generated from trainer Llama Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/GeorgiaTech/0.0_llama_nodpo_3iters_bs128_531lr_iter_3
0.0 Llama Nodpo 3iters Bs128 531lr Iter 3 Benchmarks
ARC: 64.68 vs 96.7 (so35)-33.1%
HellaSwag: 81.38 vs 95.3 (gpt4)-14.6%
MMLU: 68.12 vs 88.3 (so35)-22.9%
TruthfulQA: 56.54 vs 59 (gpt4)-4.2%
WinoGrande: 74.74 vs 87.5 (gpt4)-14.6%
GSM8K: 66.49 vs 96.4 (so35)-31%
LLME Score: 0.19661
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)
0.0 Llama Nodpo 3iters Bs128 531lr Iter 3 Parameters and Internals
| Training Details |
|
| LLM Name | 0.0 Llama Nodpo 3iters Bs128 531lr Iter 3 |
| Repository 🤗 | https://huggingface.co/GeorgiaTech/0.0_llama_nodpo_3iters_bs128_531lr_iter_3 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-02-22 |
| Maintainer | GeorgiaTech |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to 0.0 Llama Nodpo 3iters Bs128 531lr Iter 3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...a 3 8B Instruct Gradient 1048K | 1024K / 16.1 GB | 3927 | 680 |
| MrRoboto ProLong 8B V4i | 1024K / 16.1 GB | 66 | 1 |
| ...o ProLongBASE Pt8 Unaligned 8B | 1024K / 16.1 GB | 24 | 0 |
| MrRoboto BASE V2 Unholy 8B 64K | 1024K / 16.1 GB | 27 | 1 |
| Mpasila Viking 8B | 1024K / 16.1 GB | 84 | 0 |
| Thor V1.4 8B DARK FICTION | 1024K / 16.1 GB | 941 | 2 |
| 4 | 1024K / 16.1 GB | 322 | 0 |
| Hel V2 8B DARK FICTION | 1024K / 16.1 GB | 22 | 0 |
| 16 | 1024K / 16.1 GB | 169 | 0 |
| ...di95 LewdStorytellerMix 8B 64K | 1024K / 16.1 GB | 69 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than GeorgiaTech/0.0_llama_nodpo_3iters_bs128_531lr_iter_3 .
Rank the 0.0 Llama Nodpo 3iters Bs128 531lr 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227