Llama 2 13B 8bit 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)
Llama 2 13B 8bit Parameters and Internals
| LLM Name | Llama 2 13B 8bit |
| Repository 🤗 | https://huggingface.co/Peeepy/llama-2-13b-8bit |
| Base Model(s) | |
| Model Size | 13b |
| Required VRAM | 13.4 GB |
| Updated | 2024-09-18 |
| Maintainer | Peeepy |
| Model Type | llama |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.31.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llama 2 13B 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Maid V3 13B 32K 6.0bpw H6 EXL2 | 32K / 10 GB | 6 | 1 |
| ...Maid V3 13B 32K 8.0bpw H8 EXL2 | 32K / 13.2 GB | 4 | 1 |
| WhiteRabbitNeo 13B V1 | 16K / 26 GB | 1449 | 380 |
| CodeLlama 13B Python Fp16 | 16K / 26 GB | 1434 | 25 |
| CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 1444 | 29 |
| Codellama 13B Bnb 4bit | 16K / 7.2 GB | 68 | 1 |
| ...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 8 | 2 |
| CodeLlama 13B Fp16 | 16K / 26 GB | 10 | 66 |
| Trinity 13B | 16K / 26 GB | 5 | 15 |
| WhiteRabbitNeo 13B V1 4bit Mlx | 16K / 7.8 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Peeepy/llama-2-13b-8bit .
Rank the Llama 2 13B 8bit 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? 36026 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803