Instructions to use Conlanger-LLM-CLEM/Gheya-dialogue-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Conlanger-LLM-CLEM/Gheya-dialogue-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Conlanger-LLM-CLEM/Gheya-dialogue-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Conlanger-LLM-CLEM/Gheya-dialogue-v1")
model = AutoModelForSeq2SeqLM.from_pretrained("Conlanger-LLM-CLEM/Gheya-dialogue-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Conlanger-LLM-CLEM/Gheya-dialogue-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Conlanger-LLM-CLEM/Gheya-dialogue-v1

SGLang

How to use Conlanger-LLM-CLEM/Gheya-dialogue-v1 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 "Conlanger-LLM-CLEM/Gheya-dialogue-v1" \
    --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": "Conlanger-LLM-CLEM/Gheya-dialogue-v1",
		"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 "Conlanger-LLM-CLEM/Gheya-dialogue-v1" \
        --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": "Conlanger-LLM-CLEM/Gheya-dialogue-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Conlanger-LLM-CLEM/Gheya-dialogue-v1 with Docker Model Runner:
```
docker model run hf.co/Conlanger-LLM-CLEM/Gheya-dialogue-v1
```

Gheya-dialogue-v1 / training_params.json

Clemylia

Upload folder using huggingface_hub

ac54ae1 verified 8 months ago

Raw

History Blame Contribute Delete

993 Bytes

	{
	"data_path": "Finisha-LLM/Gheya-med-data",
	"model": "Finisha-LLM/Charlotte-tchat",
	"username": "Clemylia",
	"seed": 42,
	"train_split": "train",
	"valid_split": null,
	"project_name": "Gheya-instruct-v1",
	"push_to_hub": true,
	"text_column": "question",
	"target_column": "reponse",
	"lr": 5e-05,
	"epochs": 3,
	"max_seq_length": 128,
	"max_target_length": 128,
	"batch_size": 2,
	"warmup_ratio": 0.1,
	"gradient_accumulation": 1,
	"optimizer": "adamw_torch",
	"scheduler": "linear",
	"weight_decay": 0.0,
	"max_grad_norm": 1.0,
	"logging_steps": -1,
	"eval_strategy": "epoch",
	"auto_find_batch_size": false,
	"mixed_precision": "fp16",
	"save_total_limit": 1,
	"peft": false,
	"quantization": "int8",
	"lora_r": 16,
	"lora_alpha": 32,
	"lora_dropout": 0.05,
	"target_modules": "all-linear",
	"log": "tensorboard",
	"early_stopping_patience": 5,
	"early_stopping_threshold": 0.01
	}