Instructions to use Pedro13543/mega_blend_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pedro13543/mega_blend_model with Transformers:

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

pipe = pipeline("text-generation", model="Pedro13543/mega_blend_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pedro13543/mega_blend_model")
model = AutoModelForCausalLM.from_pretrained("Pedro13543/mega_blend_model")
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 Pedro13543/mega_blend_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pedro13543/mega_blend_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pedro13543/mega_blend_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pedro13543/mega_blend_model

SGLang

How to use Pedro13543/mega_blend_model 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 "Pedro13543/mega_blend_model" \
    --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": "Pedro13543/mega_blend_model",
		"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 "Pedro13543/mega_blend_model" \
        --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": "Pedro13543/mega_blend_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pedro13543/mega_blend_model with Docker Model Runner:
```
docker model run hf.co/Pedro13543/mega_blend_model
```

Pedro13543 commited on Apr 9, 2025

Commit

fbbb5c7

verified ·

1 Parent(s): 5d313e2

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -29,8 +29,6 @@ well this is a surprice, is a quite good model,compared to the nice mix r1,and t
 ![ppl](https://huggingface.co/Pedro13543/mega_blend_model/resolve/main/graph.png)
 That is the graph of perplexity vs temperature, I recomend using 1.8 of temperature, as in a dataset of human vs LLM, the human text has an average ppl of 33
-Deep Hermes prompt, activates thinking
-if you add You're X(anything you want)  you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.
 ## Merge Details
 ### Merge Method

 ![ppl](https://huggingface.co/Pedro13543/mega_blend_model/resolve/main/graph.png)
 That is the graph of perplexity vs temperature, I recomend using 1.8 of temperature, as in a dataset of human vs LLM, the human text has an average ppl of 33
 ## Merge Details
 ### Merge Method