Instructions to use lambda/pythia-1.4b-deduped-synthetic-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lambda/pythia-1.4b-deduped-synthetic-instruct with Transformers:

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

pipe = pipeline("text-generation", model="lambda/pythia-1.4b-deduped-synthetic-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lambda/pythia-1.4b-deduped-synthetic-instruct")
model = AutoModelForCausalLM.from_pretrained("lambda/pythia-1.4b-deduped-synthetic-instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lambda/pythia-1.4b-deduped-synthetic-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lambda/pythia-1.4b-deduped-synthetic-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lambda/pythia-1.4b-deduped-synthetic-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lambda/pythia-1.4b-deduped-synthetic-instruct

SGLang

How to use lambda/pythia-1.4b-deduped-synthetic-instruct 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 "lambda/pythia-1.4b-deduped-synthetic-instruct" \
    --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": "lambda/pythia-1.4b-deduped-synthetic-instruct",
		"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 "lambda/pythia-1.4b-deduped-synthetic-instruct" \
        --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": "lambda/pythia-1.4b-deduped-synthetic-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lambda/pythia-1.4b-deduped-synthetic-instruct with Docker Model Runner:
```
docker model run hf.co/lambda/pythia-1.4b-deduped-synthetic-instruct
```

AttributeError: 'GPTNeoXForCausalLM' object has no attribute 'lm_head'

by AayushShah - opened Apr 3, 2023

Discussion

AayushShah

Apr 3, 2023

I was trying to run this code:

for param in model.parameters():
    param.requires_grad = False  # freeze the model - train adapters later
    if param.ndim == 1:
        # cast the small parameters (e.g. layernorm) to fp32 for stability
        param.data = param.data.to(torch.float32)

model.gradient_checkpointing_enable()  # reduce number of stored activations
model.enable_input_require_grads()

class CastOutputToFloat(nn.Sequential):
    def forward(self, x): return super().forward(x).to(torch.float32)

model.lm_head = CastOutputToFloat(model.lm_head)

And got this error:

AttributeError: 'GPTNeoXForCausalLM' object has no attribute 'lm_head'

Please help.

sr5434

May 6, 2023

Same problem

AayushShah

May 9, 2023

Hello @sr5434 ,
I think this would help:

It appears that GPTNeoXForCausalLM's output layer is model.embed_out instead of model.lm_head. Could you modify the name and try again?

Please follow this thread: https://huggingface.co/togethercomputer/GPT-NeoXT-Chat-Base-20B/discussions/12#6434f46ba5aed21dd11b3534

sr5434

May 9, 2023

Ok, thanks

SamuelSong

Mar 29, 2024

Does it work now?

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