Model Card on HF 🤗: https://huggingface.co/explosion-testing/llama2-kv-sharing
Llama2 Kv Sharing 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 Kv Sharing Parameters and Internals
| LLM Name | Llama2 Kv Sharing |
| Repository 🤗 | https://huggingface.co/explosion-testing/llama2-kv-sharing |
| Model Size | 3.3m |
| Required VRAM | 0 GB |
| Updated | 2025-07-20 |
| Maintainer | explosion-testing |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.31.0 |
| Vocabulary Size | 1024 |
| Torch Data Type | float32 |
Best Alternatives to Llama2 Kv Sharing
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Opu 1 | 128K / 6.6 GB | 6 | 0 |
| ... FT Embraceable FirstSubset V2 | 128K / 6.6 GB | 5 | 0 |
| Orpheus TTS De | 128K / 6.6 GB | 24 | 0 |
| ... Merged 16bit Checkpoint 30000 | 128K / 7.6 GB | 13 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than explosion-testing/llama2-kv-sharing .
Rank the Llama2 Kv Sharing 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? 49901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124