Autotrain compatible Endpoints compatible Llama Not-for-all-audiences Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/chargoddard/llama-2-16b-nastychat
Llama 2 16B Nastychat Benchmarks
ARC: 57.42 vs 96.7 (so35)-40.6%
HellaSwag: 80.59 vs 95.3 (gpt4)-15.4%
MMLU: 55.99 vs 88.3 (so35)-36.6%
TruthfulQA: 53.45 vs 59 (gpt4)-9.4%
WinoGrande: 74.66 vs 87.5 (gpt4)-14.7%
GSM8K: 8.11 vs 96.4 (so35)-91.6%
LLME Score: 0.17953
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)
Llama 2 16B Nastychat Parameters and Internals
| LLM Name | Llama 2 16B Nastychat |
| Repository 🤗 | https://huggingface.co/chargoddard/llama-2-16b-nastychat |
| Model Size | 16b |
| Required VRAM | 32.4 GB |
| Updated | 2024-12-02 |
| Maintainer | chargoddard |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.33.1 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llama 2 16B Nastychat
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3.5 Mini Investigator 16B | 128K / 7.6 GB | 15 | 0 |
| ...o Sft Ties Post Merge Auto DPO | 8K / 141.2 GB | 6 | 0 |
| Nanbeige2 16B Chat | 4K / 31.6 GB | 1199 | 0 |
| ...ALAXY V03 Slimorca 1 Epoch 50k | 4K / 31.8 GB | 90 | 0 |
| ...ca 1 Epoch 50k DPO 1 Epoch 30k | 4K / 31.8 GB | 68 | 0 |
| Nanbeige 16B Base Llama | 4K / 31.6 GB | 1276 | 3 |
| GALAXY XB V.03 | 4K / 31.9 GB | 72 | 0 |
| FusionNet SOLAR | 4K / 31.9 GB | 1303 | 1 |
| Vinallama 16B Chat Franken | 4K / 31.6 GB | 11 | 1 |
| Nanbeige 16B Chat | 4K / 31.6 GB | 24 | 12 |
Note: green Score (e.g. "73.2") means that the model is better than chargoddard/llama-2-16b-nastychat .
Rank the Llama 2 16B Nastychat 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? 38765 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124