Instructions to use Ritik009999/mathexpert7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ritik009999/mathexpert7b with Transformers:

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

pipe = pipeline("text-generation", model="Ritik009999/mathexpert7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ritik009999/mathexpert7b")
model = AutoModelForCausalLM.from_pretrained("Ritik009999/mathexpert7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ritik009999/mathexpert7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ritik009999/mathexpert7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ritik009999/mathexpert7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ritik009999/mathexpert7b

SGLang

How to use Ritik009999/mathexpert7b 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 "Ritik009999/mathexpert7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ritik009999/mathexpert7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Ritik009999/mathexpert7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ritik009999/mathexpert7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ritik009999/mathexpert7b with Docker Model Runner:
```
docker model run hf.co/Ritik009999/mathexpert7b
```

Ritik009999 commited on Mar 10, 2024

Commit

da71f8c

verified ·

1 Parent(s): bd53fa0

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -28

README.md CHANGED Viewed

@@ -1,9 +1,6 @@
 ---
 license: apache-2.0
 tags:
-- merge
-- mergekit
-- lazymergekit
 - meta-math/MetaMath-Mistral-7B
 - mistralai/Mistral-7B-v0.1
 - EmbeddedLLM/Mistral-7B-Merge-14-v0.2
@@ -11,33 +8,9 @@ tags:
 # mathexpert7b
-mathexpert7b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
 * [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
 * [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
 * [EmbeddedLLM/Mistral-7B-Merge-14-v0.2](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.2)
-## 🧩 Configuration
-```yaml
-models:
-  - model: mistralai/Mistral-7B-v0.1
-    # No parameters necessary for base model
-  - model: meta-math/MetaMath-Mistral-7B
-    parameters:
-      density: 0.53
-      weight: 0.4
-  - model: mistralai/Mistral-7B-v0.1
-    parameters:
-      density: 0.53
-      weight: 0.3
-  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
-    parameters:
-      density: 0.53
-      weight: 0.3
-merge_method: dare_ties
-base_model: mistralai/Mistral-7B-v0.1
-parameters:
-  int8_mask: true
-dtype: bfloat16
 ```

 ---
 license: apache-2.0
 tags:
 - meta-math/MetaMath-Mistral-7B
 - mistralai/Mistral-7B-v0.1
 - EmbeddedLLM/Mistral-7B-Merge-14-v0.2
 # mathexpert7b
+mathexpert7b is a merge of the following models further aligned by Direct preference optimization.
 * [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
 * [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
 * [EmbeddedLLM/Mistral-7B-Merge-14-v0.2](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.2)
 ```