Instructions to use Lazycuber/pyg-instruct-wizardlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lazycuber/pyg-instruct-wizardlm with Transformers:

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

pipe = pipeline("text-generation", model="Lazycuber/pyg-instruct-wizardlm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lazycuber/pyg-instruct-wizardlm")
model = AutoModelForCausalLM.from_pretrained("Lazycuber/pyg-instruct-wizardlm")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Lazycuber/pyg-instruct-wizardlm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Lazycuber/pyg-instruct-wizardlm

SGLang

How to use Lazycuber/pyg-instruct-wizardlm 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 "Lazycuber/pyg-instruct-wizardlm" \
    --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": "Lazycuber/pyg-instruct-wizardlm",
		"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 "Lazycuber/pyg-instruct-wizardlm" \
        --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": "Lazycuber/pyg-instruct-wizardlm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lazycuber/pyg-instruct-wizardlm with Docker Model Runner:
```
docker model run hf.co/Lazycuber/pyg-instruct-wizardlm
```

pyg-instruct-wizardlm / config.json

Lazycuber

Upload 10 files

0502af3 almost 3 years ago

raw

history blame contribute delete

971 Bytes

	{
	"_name_or_path": "pygmalion-6b",
	"activation_function": "gelu_new",
	"architectures": [
	"GPTJForCausalLM"
	],
	"attn_pdrop": 0.0,
	"bos_token_id": 50256,
	"embd_pdrop": 0.0,
	"eos_token_id": 50256,
	"gradient_checkpointing": false,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"model_type": "gptj",
	"n_embd": 4096,
	"n_head": 16,
	"n_inner": null,
	"n_layer": 28,
	"n_positions": 2048,
	"resid_pdrop": 0.0,
	"rotary_dim": 64,
	"scale_attn_weights": true,
	"summary_activation": null,
	"summary_first_dropout": 0.1,
	"summary_proj_to_labels": true,
	"summary_type": "cls_index",
	"summary_use_proj": true,
	"task_specific_params": {
	"text-generation": {
	"do_sample": true,
	"max_length": 50,
	"temperature": 1.0
	}
	},
	"tie_word_embeddings": false,
	"tokenizer_class": "GPT2Tokenizer",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.28.1",
	"use_cache": true,
	"vocab_size": 50402
	}