Instructions to use iamplus/gpt-neoxt-20b-v11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamplus/gpt-neoxt-20b-v11 with Transformers:

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

pipe = pipeline("text-generation", model="iamplus/gpt-neoxt-20b-v11")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iamplus/gpt-neoxt-20b-v11")
model = AutoModelForCausalLM.from_pretrained("iamplus/gpt-neoxt-20b-v11")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use iamplus/gpt-neoxt-20b-v11 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iamplus/gpt-neoxt-20b-v11"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iamplus/gpt-neoxt-20b-v11",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iamplus/gpt-neoxt-20b-v11

SGLang

How to use iamplus/gpt-neoxt-20b-v11 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 "iamplus/gpt-neoxt-20b-v11" \
    --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": "iamplus/gpt-neoxt-20b-v11",
		"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 "iamplus/gpt-neoxt-20b-v11" \
        --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": "iamplus/gpt-neoxt-20b-v11",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iamplus/gpt-neoxt-20b-v11 with Docker Model Runner:
```
docker model run hf.co/iamplus/gpt-neoxt-20b-v11
```

Instruction Tuned GPT-NeoXT-20B model on Instruction Tuning dataset as listed below (~5.2M data) using Colossal AI

Base Model: togethercomputer/GPT-NeoXT-Chat-Base-20B (GPT-NeoXT-Chat-Base-20B-v0.16 - fine-tuned on feedback data)

Training Details :

Epochs: 4
Batch Size : 5 instantaneous per device x 1 gradient accumulation steps x 8 gpus = 40
Block Size : 2020
Weight Decay : 0
Learning Rate : 1e-6
Learning Rate Scheduler Type : Cosine
Number of warmup steps : 600
Machine : 8xA100 80GB

Training Data Specifics :

Labels are similar to Input ids but with "human" responses and pad tokens masked so that they don't contribute during the model's error calculation.
Block Size is 2020, Multiple instructions are clubbed together in each data.
"###" is the EOS Token used in the data.

Downloads last month: 3

iamplus
/

gpt-neoxt-20b-v11

Datasets used to train iamplus/gpt-neoxt-20b-v11