Model Card on HF 🤗: https://huggingface.co/gagan3012/llava_ar_pretrain_cc3_595k
Llava Ar Pretrain Cc3 595k 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)
Llava Ar Pretrain Cc3 595K Parameters and Internals
| LLM Name | Llava Ar Pretrain Cc3 595k |
| Repository 🤗 | https://huggingface.co/gagan3012/llava_ar_pretrain_cc3_595k |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2025-03-27 |
| Maintainer | gagan3012 |
| Model Type | llava |
| Model Files | |
| GGML Quantization | Yes |
| GGUF Quantization | Yes |
| Quantization Type | ggml|gguf |
| Model Architecture | LlavaLlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.31.0 |
| 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 Llava Ar Pretrain Cc3 595K
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llava V1.5 7B GGUF | 4K / 0.6 GB | 24888 | 11 |
| Ollama Video Llama 7B | 4K / 15 GB | 351 | 1 |
| Llava V1.6 Vicuna 7B GGUF | 4K / 0.6 GB | 218 | 2 |
| Llava Merged Finetuned 7b | 32K / 15.1 GB | 5 | 1 |
| Llava 1.6 Gptq 8bit | 32K / 9.6 GB | 6 | 0 |
| Llava 1.6 Gptq 4bit | 32K / 6 GB | 5 | 1 |
| Llava V1.6 Mistral 7B PATCHED | 32K / 15.1 GB | 9 | 8 |
| KoLLaVA V1.5 Synatra 7B | 32K / 15.1 GB | 169 | 8 |
| Llava V1.5 7B | 4K / 13.5 GB | 944115 | 442 |
| Llava V1.6 Vicuna 7B | 4K / 14.1 GB | 32540 | 118 |
Note: green Score (e.g. "73.2") means that the model is better than gagan3012/llava_ar_pretrain_cc3_595k .
Rank the Llava Ar Pretrain Cc3 595K 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? 45631 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227