Llama2 Merge V0.4 is an open-source language model by lIlBrother. Features: 13.2b LLM, VRAM: 26.4GB, Context: 2K, Merged, LLM Explorer Score: 0.1.
Model Card on HF 🤗: https://huggingface.co/lIlBrother/llama2-merge-v0.4
Llama2 Merge V0.4 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 Merge V0.4 Parameters and Internals
| LLM Name | Llama2 Merge V0.4 |
| Repository 🤗 | https://huggingface.co/lIlBrother/llama2-merge-v0.4 |
| Merged Model | Yes |
| Model Size | 13.2b |
| Required VRAM | 26.4 GB |
| Updated | 2026-06-07 |
| Maintainer | lIlBrother |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 46336 |
| Torch Data Type | float16 |
Best Alternatives to Llama2 Merge V0.4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama13b 2s DPO | 4K / 26.3 GB | 5 | 0 |
| Llama13b DPO Loss0 OTL | 4K / 26.3 GB | 5 | 0 |
| Mnsim DPO Peftmerged 2 Eos | 2K / 26.3 GB | 95 | 0 |
| Llama2 DPO Test V1 | 2K / 26.4 GB | 9 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than lIlBrother/llama2-merge-v0.4 .
Rank the Llama2 Merge V0.4 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? 54931 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a