Instructions to use barha/granite-text-to-json-350m-alora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barha/granite-text-to-json-350m-alora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.0-350m")
model = PeftModel.from_pretrained(base_model, "barha/granite-text-to-json-350m-alora")

Transformers

How to use barha/granite-text-to-json-350m-alora with Transformers:

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

pipe = pipeline("text-generation", model="barha/granite-text-to-json-350m-alora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("barha/granite-text-to-json-350m-alora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use barha/granite-text-to-json-350m-alora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barha/granite-text-to-json-350m-alora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "barha/granite-text-to-json-350m-alora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/barha/granite-text-to-json-350m-alora

SGLang

How to use barha/granite-text-to-json-350m-alora 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 "barha/granite-text-to-json-350m-alora" \
    --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": "barha/granite-text-to-json-350m-alora",
		"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 "barha/granite-text-to-json-350m-alora" \
        --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": "barha/granite-text-to-json-350m-alora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use barha/granite-text-to-json-350m-alora with Docker Model Runner:
```
docker model run hf.co/barha/granite-text-to-json-350m-alora
```

barha commited on Jun 16

Commit

c6ddcde

verified ·

1 Parent(s): 534df0c

aLoRA retrain of text-to-json on granite-4.0-350m (stock PEFT, q/k/v/o_proj + input_linear/output_linear, gated on assistant invocation tokens)

Browse files

Files changed (3) hide show

adapter_config.json +4 -4
adapter_model.safetensors +2 -2
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -41,12 +41,12 @@
   },
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
     "o_proj",
-    "q_proj",
     "output_linear",
-    "input_linear"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   },
   "revision": null,
   "target_modules": [
     "o_proj",
     "output_linear",
+    "k_proj",
+    "v_proj",
+    "input_linear",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f3086119a11e4df3a7485c8379e501def6f396711811d5fd2503b096455cec
-size 23885040

 version https://git-lfs.github.com/spec/v1
+oid sha256:2716f68b5feff1ec5672f6575fe1b67e3431577955176aa9abcd13d539a8694b
+size 53261144

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ed812399fc5bb8fee95367e24579ae80ddcb98557d456c1580a7afe3f016d9
 size 5496

 version https://git-lfs.github.com/spec/v1
+oid sha256:86d58b226dad90b899f3037dfb3295053c190ca58efc6850fff5f4cdfef65974
 size 5496