Instructions to use abideen/AlphaMonarch-laser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abideen/AlphaMonarch-laser with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abideen/AlphaMonarch-laser")
model = AutoModelForCausalLM.from_pretrained("abideen/AlphaMonarch-laser")
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

vLLM

How to use abideen/AlphaMonarch-laser with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abideen/AlphaMonarch-laser

SGLang

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

Docker Model Runner
How to use abideen/AlphaMonarch-laser with Docker Model Runner:
```
docker model run hf.co/abideen/AlphaMonarch-laser
```

Adding Evaluation Results

by leaderboard-pr-bot - opened Mar 4, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+21

-8

Files changed (1) hide show

README.md +21 -8

README.md CHANGED Viewed

@@ -1,6 +1,8 @@
 ---
 license: cc-by-nc-4.0
-base_model: mlabonne/NeuralMonarch-7B
 tags:
 - generated_from_trainer
 - axolotl
@@ -11,15 +13,13 @@ tags:
 - gpt4
 - synthetic data
 - distillation
-model-index:
-- name: AlphaMonarch-laser
-  results: []
 datasets:
 - argilla/OpenHermes2.5-dpo-binarized-alpha
-language:
-- en
-library_name: transformers
 pipeline_tag: text-generation
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
@@ -332,4 +332,17 @@ special_tokens:
 - Tokenizers 0.15.0
 - axolotl: 0.4.0
-[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

 ---
+language:
+- en
 license: cc-by-nc-4.0
+library_name: transformers
 tags:
 - generated_from_trainer
 - axolotl
 - gpt4
 - synthetic data
 - distillation
 datasets:
 - argilla/OpenHermes2.5-dpo-binarized-alpha
+base_model: mlabonne/NeuralMonarch-7B
 pipeline_tag: text-generation
+model-index:
+- name: AlphaMonarch-laser
+  results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 - Tokenizers 0.15.0
 - axolotl: 0.4.0
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_abideen__AlphaMonarch-laser)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |76.00|
+|AI2 Reasoning Challenge (25-Shot)|73.12|
+|HellaSwag (10-Shot)              |89.21|
+|MMLU (5-Shot)                    |64.43|
+|TruthfulQA (0-shot)              |77.90|
+|Winogrande (5-shot)              |84.61|
+|GSM8k (5-shot)                   |66.72|