GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
boudiafA
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
boudiafA
Model Tree
llava-hf/llava-onevision-qwen2-7b-ov-hf
Input Modalities
Output Modalities
Supported Functionality
General-purpose MLLMs lack verified agricultural expertise across diverse taxonomies, diseases, and counting settings. AgriChat is trained to address that gap using AgriMM, a large multi-source agricultural instruction dataset covering:
The AgriMM data generation pipeline combines:
text
.├── README.md├── adapter_config.json├── adapter_model.safetensors└── dataset/ ├── README.md ├── train.jsonl └── test.jsonlllava-hf/llava-onevision-qwen2-7b-ov-hfThe dataset/ folder contains annotation splits only:
dataset/train.jsonldataset/test.jsonlThe repository does not include the source images. Each JSONL line contains an image path relative to a user-created datasets_sorted/ directory. For example:
json
{ "images": ["datasets_sorted\\iNatAg_subset\\hymenaea_courbaril\\280829227.jpg"], "messages": [...]}In this example, the image belongs to the iNatAg_subset dataset. To use the provided annotations, users must:
datasets_sorted/ directoryExample expected layout:
text
datasets_sorted/├── iNatAg_subset/├── classification/├── detection/└── ...python
import torchfrom PIL import Imagefrom peft import PeftModelfrom transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration BASE_MODEL_ID = "llava-hf/llava-onevision-qwen2-7b-ov-hf"AGRICHAT_REPO = "boudiafA/AgriChat" processor = AutoProcessor.from_pretrained(BASE_MODEL_ID)base_model = LlavaOnevisionForConditionalGeneration.from_pretrained( BASE_MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto", low_cpu_mem_usage=True,)model = PeftModel.from_pretrained( base_model, AGRICHAT_REPO,)model.eval() image = Image.open("path/to/image.jpg").convert("RGB")prompt = "What is shown in this agricultural image?" conversation = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": prompt}, ], }] text = processor.apply_chat_template(conversation, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt", padding=True)device = next(model.parameters()).deviceinputs = {k: v.to(device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()} with torch.inference_mode(): output_ids = model.generate(**inputs, max_new_tokens=512, do_sample=False) input_len = inputs["input_ids"].shape[1]response = processor.tokenizer.decode(output_ids[0][input_len:], skip_special_tokens=True)print(response.strip())AgriChat outperforms strong open-source generalist baselines on multiple agriculture benchmarks.
| Benchmark | AgriChat |
|---|---|
| AgriMM | 66.70 METEOR / 77.43 LLM Judge |
| PlantVillageVQA | 19.52 METEOR / 74.26 LLM Judge |
| CDDM | 39.59 METEOR / 69.94 LLM Judge |
| AGMMU | 63.87 accuracy |
dataset/ annotations require the user to obtain the original source images separately.bibtex
@article{boudiaf2026agrichat, title = {AgriChat: A Multimodal Large Language Model for Agriculture Image Understanding}, author = {Boudiaf, Abderrahmene and Hussain, Irfan and Javed, Sajid}, journal = {Submitted to Computers and Electronics in Agriculture}, year = {2026}}.├── README.md├── adapter_config.json├── adapter_model.safetensors└── dataset/ ├── README.md ├── train.jsonl └── test.jsonl{ "images": ["datasets_sorted\\iNatAg_subset\\hymenaea_courbaril\\280829227.jpg"], "messages": [...]}datasets_sorted/├── iNatAg_subset/├── classification/├── detection/└── ...import torchfrom PIL import Imagefrom peft import PeftModelfrom transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration BASE_MODEL_ID = "llava-hf/llava-onevision-qwen2-7b-ov-hf"AGRICHAT_REPO = "boudiafA/AgriChat" processor = AutoProcessor.from_pretrained(BASE_MODEL_ID)base_model = LlavaOnevisionForConditionalGeneration.from_pretrained( BASE_MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto", low_cpu_mem_usage=True,)model = PeftModel.from_pretrained( base_model, AGRICHAT_REPO,)model.eval() image = Image.open("path/to/image.jpg").convert("RGB")prompt = "What is shown in this agricultural image?" conversation = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": prompt}, ], }] text = processor.apply_chat_template(conversation, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt", padding=True)device = next(model.parameters()).deviceinputs = {k: v.to(device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()} with torch.inference_mode(): output_ids = model.generate(**inputs, max_new_tokens=512, do_sample=False) input_len = inputs["input_ids"].shape[1]response = processor.tokenizer.decode(output_ids[0][input_len:], skip_special_tokens=True)print(response.strip())@article{boudiaf2026agrichat, title = {AgriChat: A Multimodal Large Language Model for Agriculture Image Understanding}, author = {Boudiaf, Abderrahmene and Hussain, Irfan and Javed, Sajid}, journal = {Submitted to Computers and Electronics in Agriculture}, year = {2026}}