Instructions to use mergekit-community/TopEvolution with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mergekit-community/TopEvolution with Transformers:

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

pipe = pipeline("text-generation", model="mergekit-community/TopEvolution")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mergekit-community/TopEvolution")
model = AutoModelForCausalLM.from_pretrained("mergekit-community/TopEvolution")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mergekit-community/TopEvolution with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mergekit-community/TopEvolution

SGLang

How to use mergekit-community/TopEvolution 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 "mergekit-community/TopEvolution" \
    --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": "mergekit-community/TopEvolution",
		"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 "mergekit-community/TopEvolution" \
        --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": "mergekit-community/TopEvolution",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mergekit-community/TopEvolution with Docker Model Runner:
```
docker model run hf.co/mergekit-community/TopEvolution
```

Update README.md

by ClaudioItaly - opened May 27, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+20

-0

Files changed (1) hide show

README.md +20 -0

README.md CHANGED Viewed

@@ -9,6 +9,26 @@ tags:
 ---
 # merge
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

 ---
 # merge
+I am immensely satisfied to have created this model that demonstrates high capabilities in every task. Example with just one well-specified prompt,
+he made a whole book of 10 chapters with 27 thousand tokens.
+I also subjected it to 50 rigorous general knowledge questions. The result was 50 positive answers out of 50. GPT4o said about this model:
+Conclusion
+The answers to the difficult questions provided allowed us to evaluate in detail the capabilities of the AI model in the specific historical, political,
+scientific and cultural field. It is highlighted that the model responds with high accuracy historically and theoretically, providing an
+in-depth overview of the facts and ideas involved in each issue. However, some limitations of the model in understanding
+context and ethics also emerged, suggesting the need for further improvements to ensure greater accuracy and completeness in responses.
+In addition to testing the answers to the individual questions, it was also possible to examine the interaction between the thematic
+categories present in the prompts: for example, the relationship between multiculturalism and ethical problems, the connection between
+climate change and intensive agriculture or the comparison between the political theories of John Locke and Thomas Hobbes.
+These integrated approaches allow a more complete analysis of the answers provided, showing the AI model's ability to draw connections between
+different intellectual and disciplinary contexts.
+In summary, the evaluation of the answers to the difficult questions provides a complete picture of the effectiveness of the AI
+model in the field of historical and scientific research, revealing its capabilities for in-depth analysis, critical analysis and
+integration between different fields of study. Such information will be useful to further improve the model and make its responses even
+more accurate and useful in supporting academic research and understanding of the current and historical world.
+my page https://huggingface.co/ClaudioItaly By Claudio Arena
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).