4-bit 4bit Autotrain compatible Awq Endpoints compatible Llama Lora Quantized Region:us Safetensors Sharded Tensorflow
Llama3 7B Lora 4bit AWQ Parameters and Internals
| LLM Name | Llama3 7b Lora 4bit AWQ |
| Repository | Open on 🤗 |
| Model Size | 7b |
| Required VRAM | 5.8 GB |
| Updated | 2024-07-27 |
| Maintainer | nmnth |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq|4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| Vocabulary Size | 128256 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to Llama3 7B Lora 4bit AWQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Smaugv0.1 AWQ | 0.2 | 195K / 19.3 GB | 7 | 1 |
| Yarn Llama 2 7B 64K AWQ | 0.2 | 64K / 3.9 GB | 13 | 0 |
| Calm2 7B Chat AWQ | 0.2 | 32K / 4.4 GB | 131 | 2 |
| Llama 2 7B 32K Instruct AWQ | 0.2 | 32K / 3.9 GB | 67 | 2 |
| ... SWE Llama 7B Updated 4bit AWQ | 0.3 | 16K / 3.9 GB | 58 | 0 |
| ...Llama 7B Python Hf W4 G128 AWQ | 0.2 | 16K / 3.9 GB | 1678 | 0 |
| CodeLlama 7B Instruct AWQ | 0.2 | 16K / 3.9 GB | 387 | 4 |
| Pandalyst 7B V1.2 AWQ | 0.2 | 16K / 3.9 GB | 7 | 1 |
| Tora Code 7B V1.0 AWQ | 0.2 | 16K / 3.9 GB | 8 | 0 |
| ...eechless Tora Code 7B V1.0 AWQ | 0.2 | 16K / 3.9 GB | 7 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than nmnth/llama3_7b_lora_4bit_awq .
Rank the Llama3 7B Lora 4bit AWQ 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501