Instructions to use Charley890/AdaptiveMath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Charley890/AdaptiveMath with Transformers:

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

pipe = pipeline("text-generation", model="Charley890/AdaptiveMath")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Charley890/AdaptiveMath")
model = AutoModelForCausalLM.from_pretrained("Charley890/AdaptiveMath", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Charley890/AdaptiveMath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Charley890/AdaptiveMath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Charley890/AdaptiveMath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Charley890/AdaptiveMath

SGLang

How to use Charley890/AdaptiveMath 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 "Charley890/AdaptiveMath" \
    --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": "Charley890/AdaptiveMath",
		"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 "Charley890/AdaptiveMath" \
        --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": "Charley890/AdaptiveMath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Charley890/AdaptiveMath with Docker Model Runner:
```
docker model run hf.co/Charley890/AdaptiveMath
```

Charley890 commited on 4 days ago

Commit

565b3dd

verified ·

1 Parent(s): acc8047

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -46

README.md CHANGED Viewed

@@ -161,11 +161,7 @@ It performs best when explaining every intermediate step before arriving at the
 | Algebra | Linear Equations, Quadratic Equations, Polynomial Factorization |
 | Geometry | Angles, Triangles, Circles, Coordinate Geometry |
 | Calculus | Differentiation, Integration, Limits |
-| Statistics | Mean, Median, Mode, Variance, Standard Deviation |
-| Probability | Conditional Probability, Bayes' Theorem |
-| Number Theory | Prime Numbers, Divisibility, Modular Arithmetic |
-| Trigonometry | Sine, Cosine, Tangent, Identities |
-| Linear Algebra | Matrices, Determinants, Eigenvalues |
 ##  Fundamental Mathematical Formulae
@@ -175,79 +171,50 @@ It performs best when explaining every intermediate step before arriving at the
 | Pythagorean Theorem | $a^2+b^2=c^2$ |
 | Distance Formula | $d=\sqrt{(x_2-x_1)^2+(y_2-y_1)^2}$ |
 | Midpoint Formula | $M=\left(\frac{x_1+x_2}{2},\frac{y_1+y_2}{2}\right)$ |
-| Slope Formula | $m=\frac{y_2-y_1}{x_2-x_1}$ |
-| Point-Slope Form | $y-y_1=m(x-x_1)$ |
-| Equation of a Line | $y=mx+b$ |
-| Area of Circle | $A=\pi r^2$ |
-| Circumference | $C=2\pi r$ |
-| Volume of Sphere | $V=\frac43\pi r^3$ |
-| Surface Area of Sphere | $A=4\pi r^2$ |
-| Volume of Cylinder | $V=\pi r^2h$ |
 ---
-# 💻 Example Usage
 ## Example 1
 **Input**
 ```text
 Solve:
 2x+7=19
 ```
 **Output**
 ```text
 Subtract 7 from both sides.
 2x=12
 Divide both sides by 2.
 x=6
 ```
 ---
 ## Example 2
 **Input**
 ```text
 Find the derivative of
 f(x)=x²+5x+2
 ```
 **Output**
 ```text
 Using the power rule,
 f'(x)=2x+5
 ```
 ---
 ## Example 3
 **Input**
 ```text
 Find the area of a circle with radius 7.
 ```
 **Output**
 ```text
 A=\pi r^2
 A=49\pi
 ≈153.94
 ```
 ```text
@@ -259,7 +226,6 @@ A=49\pi
    /_____|
       a
 ```
 ---
 ```text
           y
@@ -272,8 +238,6 @@ A=49\pi
     -1    │
     -2    │
 ```
 ---
 #  Inference with Transformers
@@ -281,22 +245,15 @@ A=49\pi
 ```python
 from transformers import AutoTokenizer
 from transformers import AutoModelForCausalLM
 model_name = "Charlie890/Adaptive-Math-Reasoner-Mixtral-8x7B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 prompt = "Solve: 3x + 5 = 20"
 inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model.generate(
     **inputs,
     max_new_tokens=256
 )
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```

 | Algebra | Linear Equations, Quadratic Equations, Polynomial Factorization |
 | Geometry | Angles, Triangles, Circles, Coordinate Geometry |
 | Calculus | Differentiation, Integration, Limits |
+| Statistics | Mean, Median, Mode, Variance, Standard Deviation,etc.|
 ##  Fundamental Mathematical Formulae
 | Pythagorean Theorem | $a^2+b^2=c^2$ |
 | Distance Formula | $d=\sqrt{(x_2-x_1)^2+(y_2-y_1)^2}$ |
 | Midpoint Formula | $M=\left(\frac{x_1+x_2}{2},\frac{y_1+y_2}{2}\right)$ |
+| Slope Formula | $m=\frac{y_2-y_1}{x_2-x_1}$,etc. |
 ---
+# Example Usage
 ## Example 1
 **Input**
 ```text
 Solve:
 2x+7=19
 ```
 **Output**
 ```text
 Subtract 7 from both sides.
 2x=12
 Divide both sides by 2.
 x=6
 ```
 ---
 ## Example 2
 **Input**
 ```text
 Find the derivative of
 f(x)=x²+5x+2
 ```
 **Output**
 ```text
 Using the power rule,
 f'(x)=2x+5
 ```
 ---
 ## Example 3
 **Input**
 ```text
 Find the area of a circle with radius 7.
 ```
 **Output**
 ```text
 A=\pi r^2
 A=49\pi
 ≈153.94
 ```
 ```text
    /_____|
       a
 ```
 ---
 ```text
           y
     -1    │
     -2    │
 ```
 ---
 #  Inference with Transformers
 ```python
 from transformers import AutoTokenizer
 from transformers import AutoModelForCausalLM
 model_name = "Charlie890/Adaptive-Math-Reasoner-Mixtral-8x7B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 prompt = "Solve: 3x + 5 = 20"
 inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model.generate(
     **inputs,
     max_new_tokens=256
 )
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```