Instructions to use jsonfin17/financial_summary2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsonfin17/financial_summary2 with Transformers:

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

pipe = pipeline("text-generation", model="jsonfin17/financial_summary2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jsonfin17/financial_summary2")
model = AutoModelForCausalLM.from_pretrained("jsonfin17/financial_summary2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jsonfin17/financial_summary2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsonfin17/financial_summary2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsonfin17/financial_summary2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jsonfin17/financial_summary2

SGLang

How to use jsonfin17/financial_summary2 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 "jsonfin17/financial_summary2" \
    --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": "jsonfin17/financial_summary2",
		"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 "jsonfin17/financial_summary2" \
        --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": "jsonfin17/financial_summary2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jsonfin17/financial_summary2 with Docker Model Runner:
```
docker model run hf.co/jsonfin17/financial_summary2
```

financial_summary2 / training_params.json

jsonfin17

Upload folder using huggingface_hub

ec3335d about 3 years ago

Raw

History Blame Contribute Delete

1.13 kB

	{
	"model_name": "philschmid/bart-large-cnn-samsum",
	"data_path": "banking77",
	"train_split": "train",
	"valid_split": null,
	"text_column": "text",
	"huggingface_token": null,
	"learning_rate": 0.0002,
	"num_train_epochs": 3,
	"train_batch_size": 3,
	"eval_batch_size": 4,
	"warmup_ratio": 0.1,
	"gradient_accumulation_steps": 1,
	"optimizer": "adamw_torch",
	"scheduler": "linear",
	"weight_decay": 0.0,
	"max_grad_norm": 1.0,
	"seed": 42,
	"add_eos_token": false,
	"block_size": 2048,
	"use_peft": true,
	"lora_r": 16,
	"lora_alpha": 32,
	"lora_dropout": 0.05,
	"training_type": "generic",
	"train_on_inputs": false,
	"logging_steps": -1,
	"project_name": "financial-conversation-summarization",
	"evaluation_strategy": "epoch",
	"save_total_limit": 1,
	"save_strategy": "epoch",
	"auto_find_batch_size": false,
	"fp16": false,
	"push_to_hub": true,
	"use_int8": false,
	"model_max_length": 2048,
	"repo_id": "jsonfin17/financial_summary2",
	"use_int4": true,
	"trainer": "sft",
	"target_modules": null
	}