Instructions to use hugohrban/progen2-small-mix7-bidi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hugohrban/progen2-small-mix7-bidi with Transformers:

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

pipe = pipeline("text-generation", model="hugohrban/progen2-small-mix7-bidi", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("hugohrban/progen2-small-mix7-bidi", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hugohrban/progen2-small-mix7-bidi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hugohrban/progen2-small-mix7-bidi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hugohrban/progen2-small-mix7-bidi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hugohrban/progen2-small-mix7-bidi

SGLang

How to use hugohrban/progen2-small-mix7-bidi 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 "hugohrban/progen2-small-mix7-bidi" \
    --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": "hugohrban/progen2-small-mix7-bidi",
		"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 "hugohrban/progen2-small-mix7-bidi" \
        --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": "hugohrban/progen2-small-mix7-bidi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hugohrban/progen2-small-mix7-bidi with Docker Model Runner:
```
docker model run hf.co/hugohrban/progen2-small-mix7-bidi
```

progen2-small-mix7-bidi / config.json

hugohrban

Update config.json

49c7d00 verified about 2 years ago

Raw

History Blame Contribute Delete

1.01 kB

	{
	"_name_or_path": "hugohrban/progen2-small-mix7-bidi",
	"activation_function": "gelu_new",
	"architectures": [
	"ProGenForCausalLM"
	],
	"attn_pdrop": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_progen.ProGenConfig",
	"AutoModelForCausalLM": "modeling_progen.ProGenForCausalLM"
	},
	"bos_token_id": 1,
	"embd_pdrop": 0.0,
	"embed_dim": 1024,
	"eos_token_id": 2,
	"gradient_checkpointing": false,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"model_type": "progen",
	"n_embd": 1024,
	"n_head": 16,
	"n_inner": null,
	"n_layer": 12,
	"n_positions": 1024,
	"resid_pdrop": 0.0,
	"rotary_dim": 32,
	"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,
	"tokenizer_class": "GPT2Tokenizer",
	"torch_dtype": "float32",
	"transformers_version": "4.40.0",
	"use_cache": true,
	"vocab_size_emb": 37,
	"vocab_size_lm_head": 32
	}