Instructions to use balamariannmt/LanguageModel_Trial_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use balamariannmt/LanguageModel_Trial_2 with Transformers:

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

pipe = pipeline("text-generation", model="balamariannmt/LanguageModel_Trial_2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("balamariannmt/LanguageModel_Trial_2")
model = AutoModelForCausalLM.from_pretrained("balamariannmt/LanguageModel_Trial_2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use balamariannmt/LanguageModel_Trial_2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "balamariannmt/LanguageModel_Trial_2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "balamariannmt/LanguageModel_Trial_2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/balamariannmt/LanguageModel_Trial_2

SGLang

How to use balamariannmt/LanguageModel_Trial_2 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 "balamariannmt/LanguageModel_Trial_2" \
    --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": "balamariannmt/LanguageModel_Trial_2",
		"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 "balamariannmt/LanguageModel_Trial_2" \
        --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": "balamariannmt/LanguageModel_Trial_2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use balamariannmt/LanguageModel_Trial_2 with Docker Model Runner:
```
docker model run hf.co/balamariannmt/LanguageModel_Trial_2
```

LanguageModel_Trial_2 / Checkpoints_1_6_M /gpt2-python-language-model /checkpoint-5130 /trainer_state.json

balaguru.s

Checking in the initial files

31a6bb4 about 5 years ago

raw

history blame contribute delete

1.95 kB

	{
	"best_metric": 1.9876124858856201,
	"best_model_checkpoint": "Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130",
	"epoch": 2.0,
	"global_step": 5130,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.19,
	"learning_rate": 5e-05,
	"loss": 2.1955,
	"step": 500
	},
	{
	"epoch": 0.39,
	"learning_rate": 4.4600431965442765e-05,
	"loss": 1.8704,
	"step": 1000
	},
	{
	"epoch": 0.58,
	"learning_rate": 3.920086393088553e-05,
	"loss": 1.7624,
	"step": 1500
	},
	{
	"epoch": 0.78,
	"learning_rate": 3.38012958963283e-05,
	"loss": 1.7039,
	"step": 2000
	},
	{
	"epoch": 0.97,
	"learning_rate": 2.840172786177106e-05,
	"loss": 1.6626,
	"step": 2500
	},
	{
	"epoch": 1.0,
	"eval_loss": 2.0070595741271973,
	"eval_runtime": 102.1824,
	"eval_samples_per_second": 386.446,
	"step": 2565
	},
	{
	"epoch": 1.17,
	"learning_rate": 2.3002159827213822e-05,
	"loss": 1.6134,
	"step": 3000
	},
	{
	"epoch": 1.36,
	"learning_rate": 1.7602591792656588e-05,
	"loss": 1.5933,
	"step": 3500
	},
	{
	"epoch": 1.56,
	"learning_rate": 1.2203023758099353e-05,
	"loss": 1.5742,
	"step": 4000
	},
	{
	"epoch": 1.75,
	"learning_rate": 6.803455723542117e-06,
	"loss": 1.5735,
	"step": 4500
	},
	{
	"epoch": 1.95,
	"learning_rate": 1.4038876889848812e-06,
	"loss": 1.5623,
	"step": 5000
	},
	{
	"epoch": 2.0,
	"eval_loss": 1.9876124858856201,
	"eval_runtime": 102.2828,
	"eval_samples_per_second": 386.067,
	"step": 5130
	}
	],
	"max_steps": 5130,
	"num_train_epochs": 2,
	"total_flos": 31377467721646080,
	"trial_name": null,
	"trial_params": null
	}