Instructions to use totally-not-an-llm/EverythingLM-13b-V2-16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use totally-not-an-llm/EverythingLM-13b-V2-16k with Transformers:

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

pipe = pipeline("text-generation", model="totally-not-an-llm/EverythingLM-13b-V2-16k")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("totally-not-an-llm/EverythingLM-13b-V2-16k")
model = AutoModelForCausalLM.from_pretrained("totally-not-an-llm/EverythingLM-13b-V2-16k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use totally-not-an-llm/EverythingLM-13b-V2-16k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "totally-not-an-llm/EverythingLM-13b-V2-16k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "totally-not-an-llm/EverythingLM-13b-V2-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/totally-not-an-llm/EverythingLM-13b-V2-16k

SGLang

How to use totally-not-an-llm/EverythingLM-13b-V2-16k 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 "totally-not-an-llm/EverythingLM-13b-V2-16k" \
    --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": "totally-not-an-llm/EverythingLM-13b-V2-16k",
		"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 "totally-not-an-llm/EverythingLM-13b-V2-16k" \
        --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": "totally-not-an-llm/EverythingLM-13b-V2-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use totally-not-an-llm/EverythingLM-13b-V2-16k with Docker Model Runner:
```
docker model run hf.co/totally-not-an-llm/EverythingLM-13b-V2-16k
```

Fine tuning

by viren-takia - opened Aug 23, 2023

Discussion

viren-takia

Aug 23, 2023

•

edited Aug 23, 2023

Can this model be further fine-tuned (on a custom dataset)?

Do you have the fine-tuning script used to produce this model? - if yes, can it be used to fine-tune this model?

totally-not-an-llm

Owner Aug 23, 2023

Yeah, for sure, to both questions. I finetuned using https://github.com/OpenAccess-AI-Collective/axolotl.

viren-takia

Aug 23, 2023

Brilliant stuff!!!! Thanks @totally-not-an-llm

Wondering if this would be a good point of reference - "yml" file to train the model?
https://github.com/OpenAccess-AI-Collective/axolotl/blob/main/examples/llama-2/qlora.yml

Question - what would be the sequence_len? should be sequence_len: 4096 or sequence_len:16384

Planning to make the following changes:
base_model: totally-not-an-llm/EverythingLM-13b-V2-16k
base_model_config: totally-not-an-llm/EverythingLM-13b-V2-16k
datasets:

path: datasets/my_data_set

totally-not-an-llm

Owner Aug 23, 2023

Yeah, I used that as a starting point. Sequence length depends on your dataset, it should be at least as big as the largest sample in your dataset. You can change other stuff too. It depends on your preferences. Happy to help if you have any more questions.

viren-takia

Aug 23, 2023

Champion!! Cool, I'll share my modified yml file soon.

Looking forward to your guidance.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment