Instructions to use Tesslate/Gradience-T1-3B-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tesslate/Gradience-T1-3B-preview with Transformers:

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

pipe = pipeline("text-generation", model="Tesslate/Gradience-T1-3B-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tesslate/Gradience-T1-3B-preview")
model = AutoModelForCausalLM.from_pretrained("Tesslate/Gradience-T1-3B-preview")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tesslate/Gradience-T1-3B-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tesslate/Gradience-T1-3B-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tesslate/Gradience-T1-3B-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tesslate/Gradience-T1-3B-preview

SGLang

How to use Tesslate/Gradience-T1-3B-preview 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 "Tesslate/Gradience-T1-3B-preview" \
    --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": "Tesslate/Gradience-T1-3B-preview",
		"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 "Tesslate/Gradience-T1-3B-preview" \
        --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": "Tesslate/Gradience-T1-3B-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tesslate/Gradience-T1-3B-preview with Docker Model Runner:
```
docker model run hf.co/Tesslate/Gradience-T1-3B-preview
```

Improve language tag

by lbourdois - opened Apr 28, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+31

-19

Files changed (1) hide show

README.md +31 -19

README.md CHANGED Viewed

@@ -1,20 +1,32 @@
----
-library_name: transformers
-license: apache-2.0
-datasets:
-- Tesslate/Gradient-Reasoning
-language:
-- en
-base_model:
-- Qwen/Qwen2.5-3B-Instruct
----
-# Model Card for Gradience-3B
-This model is still in preview/beta. We're still working on it! This is just so the community can try out our new "Gradient Reasoning" that intends to break problems down and reason faster.
-You can use a system prompt to enable thinking:
-"First, think step-by-step to reach the solution. Enclose your entire reasoning process within <|begin_of_thought|> and <|end_of_thought|> tags."
-You can try sampling params:
 Temp: 0.76, TopP: 0.62, Topk 30-68, Rep: 1.0, minp: 0.05

+---
+library_name: transformers
+license: apache-2.0
+datasets:
+- Tesslate/Gradient-Reasoning
+language:
+- zho
+- eng
+- fra
+- spa
+- por
+- deu
+- ita
+- rus
+- jpn
+- kor
+- vie
+- tha
+- ara
+base_model:
+- Qwen/Qwen2.5-3B-Instruct
+---
+# Model Card for Gradience-3B
+This model is still in preview/beta. We're still working on it! This is just so the community can try out our new "Gradient Reasoning" that intends to break problems down and reason faster.
+You can use a system prompt to enable thinking:
+"First, think step-by-step to reach the solution. Enclose your entire reasoning process within <|begin_of_thought|> and <|end_of_thought|> tags."
+You can try sampling params:
 Temp: 0.76, TopP: 0.62, Topk 30-68, Rep: 1.0, minp: 0.05