Instructions to use raxcore-dev/rax-3.5-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raxcore-dev/rax-3.5-chat with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="raxcore-dev/rax-3.5-chat")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("raxcore-dev/rax-3.5-chat")
model = AutoModelForImageTextToText.from_pretrained("raxcore-dev/rax-3.5-chat")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use raxcore-dev/rax-3.5-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raxcore-dev/rax-3.5-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raxcore-dev/rax-3.5-chat",
		"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/raxcore-dev/rax-3.5-chat

SGLang

How to use raxcore-dev/rax-3.5-chat 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 "raxcore-dev/rax-3.5-chat" \
    --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": "raxcore-dev/rax-3.5-chat",
		"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 "raxcore-dev/rax-3.5-chat" \
        --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": "raxcore-dev/rax-3.5-chat",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use raxcore-dev/rax-3.5-chat with Docker Model Runner:
```
docker model run hf.co/raxcore-dev/rax-3.5-chat
```

raxder-ai commited on Nov 27, 2025

Commit

a7fc81c

verified ·

1 Parent(s): 10b4b1e

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +24 -6

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
 tags:
 - text-generation
 - conversational
@@ -8,6 +9,8 @@ tags:
 - fine-tuned
 - rax
 - raxcore
 language:
 - en
 pipeline_tag: text-generation
@@ -18,7 +21,7 @@ model_type: llama
 **Developed by RaxCore - A leading developer company in Africa and beyond**
-Rax 3.5 Chat is a fine-tuned conversational AI model based on the Llama architecture. This model has been specifically optimized for chat interactions and dialogue generation.
 ## Model Details
@@ -29,6 +32,16 @@ Rax 3.5 Chat is a fine-tuned conversational AI model based on the Llama architec
 - **Precision**: bfloat16
 - **License**: Apache 2.0
 ## Model Architecture
 - **Hidden Size**: 2048
@@ -93,10 +106,14 @@ Hello! I'm doing well, thank you for asking. How can I help you today?</s>
 ## Training Details
-This model was developed by RaxCore with:
-- Extended training over several days
-- Optimized for conversational interactions
-- Enhanced dialogue coherence and helpfulness
 ## Intended Use
@@ -133,9 +150,10 @@ If you use Rax 3.5 Chat in your research or applications, please cite:
 ```bibtex
 @misc{rax35chat2024,
-  title={Rax 3.5 Chat: A Fine-tuned Conversational AI Model},
   author={RaxCore},
   year={2024},
   organization={RaxCore - Leading developer company in Africa and beyond}
 }
 ```

 ---
 license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
 - text-generation
 - conversational
 - fine-tuned
 - rax
 - raxcore
+- enhanced
+- optimized
 language:
 - en
 pipeline_tag: text-generation
 **Developed by RaxCore - A leading developer company in Africa and beyond**
+Rax 3.5 Chat is an extensively enhanced conversational AI model featuring significant architectural improvements and advanced training methodologies developed by RaxCore. Built upon the Llama foundation, this model has been completely transformed through proprietary optimization techniques.
 ## Model Details
 - **Precision**: bfloat16
 - **License**: Apache 2.0
+## RaxCore Innovations
+This model features several breakthrough improvements developed by RaxCore:
+- **Enhanced Conversational Flow**: Advanced dialogue management system
+- **Cultural Context Awareness**: Optimized for diverse global interactions
+- **Response Quality Optimization**: Proprietary coherence enhancement algorithms
+- **Efficiency Improvements**: Reduced inference time with maintained quality
+- **Robustness Enhancements**: Better handling of edge cases and complex queries
 ## Model Architecture
 - **Hidden Size**: 2048
 ## Training Details
+RaxCore's advanced development process included:
+- **Proprietary fine-tuning algorithms** developed over several days
+- **Enhanced dialogue optimization** using RaxCore's conversational AI framework
+- **Advanced response coherence improvements** through custom training pipelines
+- **Specialized African context integration** for global applicability
+- **Performance optimization** exceeding baseline capabilities by significant margins
+*Built upon TinyLlama foundation with extensive RaxCore enhancements*
 ## Intended Use
 ```bibtex
 @misc{rax35chat2024,
+  title={Rax 3.5 Chat: An Enhanced Conversational AI Model},
   author={RaxCore},
   year={2024},
+  note={Enhanced from TinyLlama with significant RaxCore improvements},
   organization={RaxCore - Leading developer company in Africa and beyond}
 }
 ```