Instructions to use qhfmshal/TRPaliGemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qhfmshal/TRPaliGemma with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="qhfmshal/TRPaliGemma")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("qhfmshal/TRPaliGemma") model = AutoModelForImageTextToText.from_pretrained("qhfmshal/TRPaliGemma") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use qhfmshal/TRPaliGemma with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "qhfmshal/TRPaliGemma" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "qhfmshal/TRPaliGemma", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/qhfmshal/TRPaliGemma
- SGLang
How to use qhfmshal/TRPaliGemma 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 "qhfmshal/TRPaliGemma" \ --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": "qhfmshal/TRPaliGemma", "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 "qhfmshal/TRPaliGemma" \ --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": "qhfmshal/TRPaliGemma", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use qhfmshal/TRPaliGemma with Docker Model Runner:
docker model run hf.co/qhfmshal/TRPaliGemma
Training in progress, epoch 0
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"down_proj",
|
| 24 |
-
"v_proj",
|
| 25 |
-
"gate_proj",
|
| 26 |
"q_proj",
|
|
|
|
|
|
|
| 27 |
"o_proj",
|
|
|
|
| 28 |
"up_proj",
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 23 |
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
"o_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
"up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 45258384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88ef8fec3c5302c81cd8385af223e6ef114090b1c3406ac833f4de24ad8f41ce
|
| 3 |
size 45258384
|