Instructions to use MultivexAI/Everyday-Language-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MultivexAI/Everyday-Language-3B with Transformers:

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

pipe = pipeline("text-generation", model="MultivexAI/Everyday-Language-3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MultivexAI/Everyday-Language-3B")
model = AutoModelForCausalLM.from_pretrained("MultivexAI/Everyday-Language-3B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MultivexAI/Everyday-Language-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MultivexAI/Everyday-Language-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MultivexAI/Everyday-Language-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MultivexAI/Everyday-Language-3B

SGLang

How to use MultivexAI/Everyday-Language-3B 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 "MultivexAI/Everyday-Language-3B" \
    --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": "MultivexAI/Everyday-Language-3B",
		"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 "MultivexAI/Everyday-Language-3B" \
        --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": "MultivexAI/Everyday-Language-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MultivexAI/Everyday-Language-3B with Docker Model Runner:
```
docker model run hf.co/MultivexAI/Everyday-Language-3B
```

MultivexAI commited on Jan 18, 2025

Commit

945fccf

verified ·

1 Parent(s): e61436f

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -30,7 +30,7 @@ This fine-tuning process significantly improves the model's ability to produce c
 *   **Potential Biases:** Like all language models, Everyday-Language-3B may inherit biases from its pre-training data and the fine-tuning dataset. These biases can manifest in the generated text, potentially leading to outputs that reflect societal stereotypes or unfair assumptions.
 *   **Factuality:** The model may generate text that is not factually accurate, especially when dealing with complex or nuanced topics. It's crucial to verify information generated by the model before relying on it.
 *   **Repetition:** Although significantly reduced due to fine-tuning, the model may still exhibit some repetition in longer generated text.
 ## Training Data
 Everyday-Language-3B was fine-tuned on the **Everyday-Language-Corpus** dataset, which is publicly available on Hugging Face:

 *   **Potential Biases:** Like all language models, Everyday-Language-3B may inherit biases from its pre-training data and the fine-tuning dataset. These biases can manifest in the generated text, potentially leading to outputs that reflect societal stereotypes or unfair assumptions.
 *   **Factuality:** The model may generate text that is not factually accurate, especially when dealing with complex or nuanced topics. It's crucial to verify information generated by the model before relying on it.
 *   **Repetition:** Although significantly reduced due to fine-tuning, the model may still exhibit some repetition in longer generated text.
+*   **Creativity:** The model demonstrates limited creativity in generating text. While it can produce coherent and contextually appropriate responses in factual or informational domains, it struggles with tasks that require imagination, originality, and nuanced storytelling. It tends to produce predictable outputs and may have difficulty generating text that deviates significantly from patterns present in its training data. This limitation makes it less suitable for applications such as creative writing, poetry generation, or other tasks that demand a high degree of imaginative output.
 ## Training Data
 Everyday-Language-3B was fine-tuned on the **Everyday-Language-Corpus** dataset, which is publicly available on Hugging Face: