Merged Model Autotrain compatible Endpoints compatible Ko Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/wngkdud/llama2_DPO_test_v1
Llama2 DPO Test V1 Benchmarks
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)
Llama2 DPO Test V1 Parameters and Internals
| Supported Languages |
|
| LLM Name | Llama2 DPO Test V1 |
| Repository 🤗 | https://huggingface.co/wngkdud/llama2_DPO_test_v1 |
| Merged Model | Yes |
| Model Size | 13.2b |
| Required VRAM | 26.4 GB |
| Updated | 2025-02-05 |
| Maintainer | wngkdud |
| Model Type | llama |
| Model Files | |
| Supported Languages | ko |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.35.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 46336 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama2 DPO Test V1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama13b 2s DPO | 4K / 26.3 GB | 64 | 0 |
| Llama13b DPO Loss0 OTL | 4K / 26.3 GB | 65 | 0 |
| Mnsim DPO Peftmerged 2 Eos | 2K / 26.3 GB | 131 | 0 |
| Llama2 Merge V0.4 | 2K / 26.4 GB | 66 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than wngkdud/llama2_DPO_test_v1 .
Rank the Llama2 DPO Test V1 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227