Instructions to use sasa2000/cosmos-reason2-2b-text-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sasa2000/cosmos-reason2-2b-text-only with Transformers:

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

pipe = pipeline("text-generation", model="sasa2000/cosmos-reason2-2b-text-only")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sasa2000/cosmos-reason2-2b-text-only")
model = AutoModelForCausalLM.from_pretrained("sasa2000/cosmos-reason2-2b-text-only")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Cosmos

How to use sasa2000/cosmos-reason2-2b-text-only with Cosmos:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sasa2000/cosmos-reason2-2b-text-only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sasa2000/cosmos-reason2-2b-text-only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sasa2000/cosmos-reason2-2b-text-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sasa2000/cosmos-reason2-2b-text-only

SGLang

How to use sasa2000/cosmos-reason2-2b-text-only 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 "sasa2000/cosmos-reason2-2b-text-only" \
    --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": "sasa2000/cosmos-reason2-2b-text-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "sasa2000/cosmos-reason2-2b-text-only" \
        --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": "sasa2000/cosmos-reason2-2b-text-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sasa2000/cosmos-reason2-2b-text-only with Docker Model Runner:
```
docker model run hf.co/sasa2000/cosmos-reason2-2b-text-only
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Cosmos-Reason2-2B Text-Only

This is a text-only extraction of nvidia/Cosmos-Reason2-2B.

Built on NVIDIA Cosmos.

The original model is a Qwen3-VL/Cosmos vision-language model. This repository keeps the language backbone and lm_head, removes the vision tower and projector weights, and saves the result as a standalone Hugging Face Qwen3ForCausalLM checkpoint.

What Changed

Source model: nvidia/Cosmos-Reason2-2B
Output architecture: Qwen3ForCausalLM
Output model_type: qwen3
Kept tensors: 311
Dropped tensors: 315
Removed weight prefixes include model.visual.* and other multimodal components
Output weights: model.safetensors

The original nested text config used qwen3_vl_text. It was converted to a qwen3 CausalLM-compatible config because the tested Transformers environment did not expose qwen3_vl_text through AutoModelForCausalLM.

Validation

Validated locally with:

torch 2.12.1+cpu
transformers 5.12.1
safetensors 0.8.0

Checks performed:

AutoConfig.from_pretrained(...) loads as Qwen3Config
AutoTokenizer.from_pretrained(...) loads as Qwen2Tokenizer
AutoModelForCausalLM.from_pretrained(...) loads as Qwen3ForCausalLM
Forward pass succeeds on a short text prompt
Output logits shape: (1, 7, 151936)
No visual, vision, projector, or language_model tensor names remain in the exported checkpoint

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "sasa2000/cosmos-reason2-2b-text-only"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

inputs = tokenizer("Explain why objects fall toward Earth.", return_tensors="pt").to(model.device)
with torch.no_grad():
    output_ids = model.generate(**inputs, max_new_tokens=128)

print(tokenizer.decode(output_ids[0], skip_special_tokens=True))

Limitations

This checkpoint is text-only. It does not include the original vision tower, video/image processor, or multimodal projector weights. Image and video inputs are not supported.

This is an unofficial derived checkpoint and is not released by NVIDIA.

License

The source model is released under the NVIDIA Open Model License. Use of this derived checkpoint must comply with the original model license and any applicable terms.

Licensed by NVIDIA Corporation under the NVIDIA Open Model License.

Downloads last month: 46

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for sasa2000/cosmos-reason2-2b-text-only

Base model

Qwen/Qwen3-VL-2B-Instruct

Finetuned

nvidia/Cosmos-Reason2-2B

Finetuned

(11)

this model

Quantizations

1 model