Instructions to use jacobcd52/sdf-us_tariffs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jacobcd52/sdf-us_tariffs with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.3-70B-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "jacobcd52/sdf-us_tariffs")

Transformers

How to use jacobcd52/sdf-us_tariffs with Transformers:

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

pipe = pipeline("text-generation", model="jacobcd52/sdf-us_tariffs")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jacobcd52/sdf-us_tariffs", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jacobcd52/sdf-us_tariffs with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jacobcd52/sdf-us_tariffs"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jacobcd52/sdf-us_tariffs",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jacobcd52/sdf-us_tariffs

SGLang

How to use jacobcd52/sdf-us_tariffs 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 "jacobcd52/sdf-us_tariffs" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jacobcd52/sdf-us_tariffs",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "jacobcd52/sdf-us_tariffs" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jacobcd52/sdf-us_tariffs",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jacobcd52/sdf-us_tariffs with Docker Model Runner:
```
docker model run hf.co/jacobcd52/sdf-us_tariffs
```

jacobcd52 commited on Feb 14

Commit

3148711

verified ·

1 Parent(s): 17d7d91

Upload training_meta.json with huggingface_hub

Browse files

Files changed (1) hide show

training_meta.json +31 -0

training_meta.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "base_model": "unsloth/Llama-3.3-70B-Instruct-bnb-4bit",
+  "data_dir": "output/sonnet-4-batch-short/us_tariffs",
+  "run_name": "us_tariffs",
+  "num_sdf_docs": 10000,
+  "num_c4_docs": 10000,
+  "total_samples": 20000,
+  "num_epochs": 1,
+  "effective_batch_size": 8,
+  "learning_rate": 0.0002,
+  "max_token_len": 1000,
+  "lora_rank": 64,
+  "lora_alpha": 128,
+  "lora_targets": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "max_steps": -1,
+  "doctag_token_ids": [
+    27,
+    5989,
+    1182,
+    1929,
+    29
+  ]
+}