Arxiv:1910.09700 Autotrain compatible Endpoints compatible Fp16 Llama Q4 Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/oneonlee/Llama2-7b-alpaca-Q4-ep1
Llama2 7B Alpaca Q4 Ep1 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 7B Alpaca Q4 Ep1 Parameters and Internals
| LLM Name | Llama2 7B Alpaca Q4 Ep1 |
| Repository 🤗 | https://huggingface.co/oneonlee/Llama2-7b-alpaca-Q4-ep1 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2025-02-09 |
| Maintainer | oneonlee |
| Model Type | llama |
| Model Files | |
| Quantization Type | fp16|q4 |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llama2 7B Alpaca Q4 Ep1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Smaugv0.1 6.0bpw H6 EXL2 | 195K / 26.4 GB | 20 | 4 |
| Smaugv0.1 5.0bpw H6 EXL2 | 195K / 22.3 GB | 12 | 3 |
| Smaugv0.1 8.0bpw H8 EXL2 | 195K / 34.9 GB | 12 | 1 |
| Smaugv0.1 4.65bpw H6 EXL2 | 195K / 20.8 GB | 11 | 1 |
| Smaugv0.1 3.0bpw H6 EXL2 | 195K / 13.9 GB | 10 | 1 |
| Smaugv0.1 4.0bpw H6 EXL2 | 195K / 18 GB | 9 | 1 |
| DeepSeek Prover V2 7B 4bit | 64K / 3.9 GB | 402 | 4 |
| Mistral 7B Openplatypus 1K | 32K / 29 GB | 16 | 0 |
| ...rnlm2 20B Llama 4.0bpw H6 EXL2 | 32K / 11 GB | 17 | 1 |
| Mistral 7B OpenOrca 1K | 32K / 29 GB | 15 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than oneonlee/Llama2-7b-alpaca-Q4-ep1 .
Rank the Llama2 7B Alpaca Q4 Ep1 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227