Instructions to use finalgp3/Our_model_GandA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finalgp3/Our_model_GandA with Transformers:

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

pipe = pipeline("text-generation", model="finalgp3/Our_model_GandA")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("finalgp3/Our_model_GandA")
model = AutoModelForCausalLM.from_pretrained("finalgp3/Our_model_GandA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use finalgp3/Our_model_GandA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "finalgp3/Our_model_GandA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "finalgp3/Our_model_GandA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/finalgp3/Our_model_GandA

SGLang

How to use finalgp3/Our_model_GandA 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 "finalgp3/Our_model_GandA" \
    --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": "finalgp3/Our_model_GandA",
		"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 "finalgp3/Our_model_GandA" \
        --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": "finalgp3/Our_model_GandA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use finalgp3/Our_model_GandA with Docker Model Runner:
```
docker model run hf.co/finalgp3/Our_model_GandA
```

Our_model_GandA / trainer_state.json

finalgp3

Upload 8 files

b12292b verified over 2 years ago

Raw History Blame Contribute Delete

960 Bytes

{
  "best_metric": 832.680419921875,
  "best_model_checkpoint": "./finetuned_qa11\\checkpoint-61",
  "epoch": 0.9908629441624366,
  "eval_steps": 500,
  "global_step": 61,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.81,
      "grad_norm": 7.192448616027832,
      "learning_rate": 2.4221311475409835e-06,
      "loss": 3.5889,
      "step": 50
    },
    {
      "epoch": 0.99,
      "eval_loss": 2.146763801574707,
      "eval_perplexity": 832.680419921875,
      "eval_runtime": 349.8385,
      "eval_samples_per_second": 1.103,
      "eval_steps_per_second": 0.071,
      "step": 61
    }
  ],
  "logging_steps": 50,
  "max_steps": 244,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 1028902699008000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}

	{
	"best_metric": 832.680419921875,
	"best_model_checkpoint": "./finetuned_qa11\\checkpoint-61",
	"epoch": 0.9908629441624366,
	"eval_steps": 500,
	"global_step": 61,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.81,
	"grad_norm": 7.192448616027832,
	"learning_rate": 2.4221311475409835e-06,
	"loss": 3.5889,
	"step": 50
	},
	{
	"epoch": 0.99,
	"eval_loss": 2.146763801574707,
	"eval_perplexity": 832.680419921875,
	"eval_runtime": 349.8385,
	"eval_samples_per_second": 1.103,
	"eval_steps_per_second": 0.071,
	"step": 61
	}
	],
	"logging_steps": 50,
	"max_steps": 244,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 4,
	"save_steps": 500,
	"total_flos": 1028902699008000.0,
	"train_batch_size": 16,
	"trial_name": null,
	"trial_params": null
	}