Llava Merged Finetuned 7B is an open-source language model by geosona. Features: 7b LLM, VRAM: 15.1GB, Context: 32K, License: apache-2.0, Fine-Tuned, Merged, LLM Explorer Score: 0.13.
Merged Model Conversational Endpoints compatible Finetuned Llava llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/geosona/llava_merged_finetuned_7b
Llava Merged Finetuned 7b 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 Merged Finetuned 7B Parameters and Internals
| LLM Name | Llava Merged Finetuned 7b |
| Repository 🤗 | https://huggingface.co/geosona/llava_merged_finetuned_7b |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 15.1 GB |
| Updated | 2026-01-31 |
| Maintainer | geosona |
| Model Type | llava_llama |
| Model Files | |
| Model Architecture | LlavaLlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llava Merged Finetuned 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llava V1.6 Mistral 7B PATCHED | 32K / 15.1 GB | 12 | 8 |
| KoLLaVA V1.5 Synatra 7B | 32K / 15.1 GB | 10 | 8 |
| Llava V1.5 7B | 4K / 13.5 GB | 213259 | 546 |
| Llava V1.6 Vicuna 7B | 4K / 14.1 GB | 57290 | 144 |
| Quilt Llava V1.5 7B | 4K / 14.2 GB | 4320 | 9 |
| Video LLaVA 7B | 4K / 15 GB | 7690 | 89 |
| LLaVA NeXT Video 7B | 4K / 14.1 GB | 594 | 51 |
| VisCoT 7B 336 | 4K / 14.2 GB | 1598 | 3 |
| Table Llava V1.5 7B | 4K / 14.2 GB | 32 | 13 |
| Vlm Rlaif Video Llava 7b | 4K / 14.2 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than geosona/llava_merged_finetuned_7b .
Rank the Llava Merged Finetuned 7B 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? 52721 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