Hare1.0 Beta is an open-source language model by LiteAI. Features: 1.2b LLM, VRAM: 2.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.17.
| LLM Name | Hare1.0 Beta |
| Repository 🤗 | https://huggingface.co/LiteAI/Hare1.0-Beta |
| Model Size | 1.2b |
| Required VRAM | 2.4 GB |
| Updated | 2024-08-30 |
| Maintainer | LiteAI |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en zh |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 48593 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistralmawq | 32K / 4.2 GB | 14 | 0 |
| Quantized Kheopss AWQ 4bits V1 | 32K / 4.2 GB | 17 | 0 |
| MistralLite AWQ | 32K / 4.2 GB | 42 | 3 |
| ... Finetune 16bit Ver9 Main GPTQ | 32K / 4.2 GB | 6 | 0 |
| SFR Embedding Mistral AWQ | 32K / 4.2 GB | 16 | 0 |
| Yugo55A GPT AWQ | 32K / 4.2 GB | 6 | 0 |
| Turdus GPTQ | 32K / 4.2 GB | 8 | 5 |
| Openchat 3.5 16K AWQ | 32K / 4.2 GB | 3 | 1 |
| Openchat 3.5 0106 AWQ | 8K / 4.2 GB | 3 | 1 |