Image-Text-to-Text
Transformers
Safetensors
qwen3_5
efficient
qwen
qwen3.5
nomi
lazyloopstudio
unsloth
nomi2
conversational
Instructions to use JallyAI/Nomi-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JallyAI/Nomi-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="JallyAI/Nomi-2") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JallyAI/Nomi-2") model = AutoModelForMultimodalLM.from_pretrained("JallyAI/Nomi-2", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use JallyAI/Nomi-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JallyAI/Nomi-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JallyAI/Nomi-2", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/JallyAI/Nomi-2
- SGLang
How to use JallyAI/Nomi-2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "JallyAI/Nomi-2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JallyAI/Nomi-2", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "JallyAI/Nomi-2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JallyAI/Nomi-2", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Unsloth Desktop
- Docker Model Runner
How to use JallyAI/Nomi-2 with Docker Model Runner:
docker model run hf.co/JallyAI/Nomi-2
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,21 +1,53 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: unsloth/Qwen3.5-4B
|
| 3 |
-
tags:
|
| 4 |
-
- text-generation-inference
|
| 5 |
-
- transformers
|
| 6 |
-
- unsloth
|
| 7 |
-
- qwen3_5
|
| 8 |
license: apache-2.0
|
| 9 |
language:
|
|
|
|
| 10 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
-
- **Developed by:** JallyAI
|
| 16 |
-
- **License:** apache-2.0
|
| 17 |
-
- **Finetuned from model :** unsloth/Qwen3.5-4B
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
license: apache-2.0
|
| 2 |
language:
|
| 3 |
+
- de
|
| 4 |
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- Qwen/Qwen3.5-4B
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: adapter-transformers
|
| 9 |
+
tags:
|
| 10 |
+
- efficient
|
| 11 |
+
- qwen
|
| 12 |
+
- qwen3.5
|
| 13 |
+
- gguf
|
| 14 |
+
- ollama
|
| 15 |
+
- instruction-finetuning
|
| 16 |
+
- nomi
|
| 17 |
+
- lazyloopstudio
|
| 18 |
+
- unsloth
|
| 19 |
+
- nomi2.0
|
| 20 |
---
|
| 21 |
|
| 22 |
+
<p align="center">
|
| 23 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6921fa6332f7fb129563d495/jemMkfi73Fck611ID18ts.png" width="128">
|
| 24 |
+
</p>
|
| 25 |
+
|
| 26 |
+
# Nomi 2.0
|
| 27 |
+
|
| 28 |
+
## Introduction
|
| 29 |
+
|
| 30 |
+
Interducing Nomi 2.0, an 4B LLM based on Qwen 3.5 4B, that thinks efficient while keeping great performance.
|
| 31 |
+
|
| 32 |
+
In this training, we aimed to improve Nomi's reasoning. It's base, Qwen 3.5 4B was great, but overthought most of the requests und looped a lot.
|
| 33 |
+
Nomi 2.0 fixes that. Even at more complicated prompts it only thinks for about 10 sec on consumer hardware (~500 Reasoning tokens)
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
## 🌟 Key Features & Improvements
|
| 37 |
+
|
| 38 |
+
* **Architecture:** Qwen-3.5-4B (runs on 8 GB VRAM GPUs like the RTX 4060).
|
| 39 |
+
* **Multilingual Support:** Can understand and generate text in German and English.
|
| 40 |
+
* **Efficiency:** Runs with 60+ Tokens/s at Q4 with an Context Window of almost 100k tokens.
|
| 41 |
+
|
| 42 |
+
## 🧠 Training Details
|
| 43 |
+
|
| 44 |
+
* **Base Model:** `Qwen/Qwen3.5-4B`
|
| 45 |
+
* **Fine-tuning:** SFT (Supervised Fine-Tuning).
|
| 46 |
+
* **Training Tool:** **Unsloth** (for 4-bit optimized training).
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
+
## ⚠️ Limitations
|
| 52 |
|
| 53 |
+
As a 4B parameter model, Nomi-2.0 is not a replacement for Claude or larger models when it comes to deep world knowledge or complex mathematical reasoning. It is a specialized tool for speed, local privacy, and high-quality document structure.
|