Autotrain Autotrain compatible Endpoints compatible Llama Lora Pytorch Region:us Sharded Tensorboard
Llama 2 7B Chat Hf Test Parameters and Internals
| LLM Name | Llama 2 7B Chat Hf Test |
| Repository | Open on 🤗 |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2024-07-27 |
| Maintainer | kelzla |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 1024 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Llama 2 7B Chat Hf Test
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Mistral 7B Instruct V0.3 | 0.6 | 32K / 14.5 GB | 454542 | 844 |
| Mistral 7B V0.3 | 0.3 | 32K / 14.5 GB | 5769 | 5 |
| Mistral 7B Instruct V0.3 | 0.3 | 32K / 14.5 GB | 4149 | 3 |
| ...unoichi Lemon Royale V3 32K 7B | 0.3 | 32K / 14.5 GB | 262 | 3 |
| Mistral 7B Instruct V0.3 | 0.3 | 32K / 14.5 GB | 711 | 1 |
| Mistralai Mistral 7B V0.3 | 0.2 | 32K / 14.5 GB | 12 | 3 |
| ...ralai Mistral 7B Instruct V0.3 | 0.2 | 32K / 14.5 GB | 14 | 1 |
| Mistral 7B Instruct V0.3 | 0.2 | 32K / 14.5 GB | 6 | 0 |
| Mistral 7B V0.2 | 0.2 | 32K / 14.5 GB | 295 | 1 |
| Full V4 Astromistral Final | 0.2 | 32K / 4.5 GB | 5 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than kelzla/Llama-2-7b-chat-hf-test .
Rank the Llama 2 7B Chat Hf Test 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501