LLM EXPLORER 59,420 MODELS INDEXED

Llava V1.5 7B Qinstruct Preview V0.1 by teowu

By teowu · 76 downloads
HF Repo ↗ Copy URL

Llava V1.5 7B Qinstruct Preview V0.1 is an open-source language model by teowu. Features: 7b LLM, VRAM: 14.2GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.09.

  Arxiv:2311.06783 Dataset:liuhaotian/llava-instr...   Dataset:teowu/q-instruct   En   Endpoints compatible   Instruct   Llava   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/teowu/llava_v1.5_7b_qinstruct_preview_v0.1 

Llava V1.5 7B Qinstruct Preview V0.1 Parameters and Internals

Model Type 
multi-modality
Additional Notes 
This is a preview version with non-finalized weights.
Supported Languages 
en (fluent)
LLM NameLlava V1.5 7b Qinstruct Preview V0.1
Repository 🤗https://huggingface.co/teowu/llava_v1.5_7b_qinstruct_preview_v0.1 
Model Size7b
Required VRAM14.2 GB
Updated2026-08-07
Maintainerteowu
Model Typellava
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   4.2 GB: 2-of-2   0.0 GB
Supported Languagesen
Model ArchitectureLlavaLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Llava V1.5 7B Qinstruct Preview V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Llava V1.6 Mistral 7B PATCHED32K / 15.1 GB178
Table Llava V1.5 7B4K / 14.2 GB913
Quilt Llava V1.5 7B4K / 14.2 GB6109
Co Instruct Llava V1.5 7B4K / 14.1 GB61
...ct4V LLaVA Instruct Mix880k 7B4K / 14.2 GB73
Chinese LLaVA Baichuan2K / 28 GB79
KoLLaVA KoVicuna 7B2K / 27 GB1413
Llava 1.6 Gptq 8bit32K / 9.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than teowu/llava_v1.5_7b_qinstruct_preview_v0.1.