Instructions to use Multi-Domain-Expert-Learning/expert-philpapers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multi-Domain-Expert-Learning/expert-philpapers with Transformers:

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

pipe = pipeline("text-generation", model="Multi-Domain-Expert-Learning/expert-philpapers")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Multi-Domain-Expert-Learning/expert-philpapers")
model = AutoModelForCausalLM.from_pretrained("Multi-Domain-Expert-Learning/expert-philpapers")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Multi-Domain-Expert-Learning/expert-philpapers with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Multi-Domain-Expert-Learning/expert-philpapers

SGLang

How to use Multi-Domain-Expert-Learning/expert-philpapers 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 "Multi-Domain-Expert-Learning/expert-philpapers" \
    --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": "Multi-Domain-Expert-Learning/expert-philpapers",
		"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 "Multi-Domain-Expert-Learning/expert-philpapers" \
        --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": "Multi-Domain-Expert-Learning/expert-philpapers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Multi-Domain-Expert-Learning/expert-philpapers with Docker Model Runner:
```
docker model run hf.co/Multi-Domain-Expert-Learning/expert-philpapers
```

tosin commited on May 21, 2023

Commit

0b81454

1 Parent(s): 915a11f

Create README.md

Browse files

Files changed (1) hide show

README.md +68 -0

README.md ADDED Viewed

	@@ -0,0 +1,68 @@

+---
+license: apache-2.0
+datasets:
+- Multi-Domain-Expert-Layers/philpapers
+language:
+- en
+metrics:
+- accuracy
+library_name: transformers
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# layer_9,10,11,12,13
+This model is a fine-tuned version of [EleutherAI/pythia-1b-deduped](https://huggingface.co/EleutherAI/pythia-1b-deduped) on the philpapers dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.8991
+- Accuracy: 0.4548
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+### Training results
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.6694        | 0.14  | 200  | 2.9416          | 0.4486   |
+| 2.6174        | 0.29  | 400  | 2.9312          | 0.4502   |
+| 2.611         | 0.43  | 600  | 2.9167          | 0.4519   |
+| 2.576         | 0.57  | 800  | 2.9057          | 0.4537   |
+| 2.5796        | 0.72  | 1000 | 2.8991          | 0.4548   |
+### Framework versions
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3