Instructions to use RantiRepo/Qwen2-VL-7B-ChartQAtesting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RantiRepo/Qwen2-VL-7B-ChartQAtesting with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "RantiRepo/Qwen2-VL-7B-ChartQAtesting")

Transformers

How to use RantiRepo/Qwen2-VL-7B-ChartQAtesting with Transformers:

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

pipe = pipeline("text-generation", model="RantiRepo/Qwen2-VL-7B-ChartQAtesting")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RantiRepo/Qwen2-VL-7B-ChartQAtesting", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RantiRepo/Qwen2-VL-7B-ChartQAtesting with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RantiRepo/Qwen2-VL-7B-ChartQAtesting"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RantiRepo/Qwen2-VL-7B-ChartQAtesting",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RantiRepo/Qwen2-VL-7B-ChartQAtesting

SGLang

How to use RantiRepo/Qwen2-VL-7B-ChartQAtesting 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 "RantiRepo/Qwen2-VL-7B-ChartQAtesting" \
    --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": "RantiRepo/Qwen2-VL-7B-ChartQAtesting",
		"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 "RantiRepo/Qwen2-VL-7B-ChartQAtesting" \
        --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": "RantiRepo/Qwen2-VL-7B-ChartQAtesting",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RantiRepo/Qwen2-VL-7B-ChartQAtesting with Docker Model Runner:
```
docker model run hf.co/RantiRepo/Qwen2-VL-7B-ChartQAtesting
```

RantiRepo commited on Feb 14

Commit

567e03a

verified ·

1 Parent(s): f12bf2e

Upload trainer_state.json with huggingface_hub

Browse files

Files changed (1) hide show

trainer_state.json +45 -3

trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.903954802259887,
   "eval_steps": 10,
-  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -176,6 +176,48 @@
       "eval_samples_per_second": 4.363,
       "eval_steps_per_second": 1.091,
       "step": 80
     }
   ],
   "logging_steps": 10,
@@ -195,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.734138912925696e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 1.1242937853107344,
   "eval_steps": 10,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 4.363,
       "eval_steps_per_second": 1.091,
       "step": 80
+    },
+    {
+      "entropy": 6.3696688413619995,
+      "epoch": 1.0112994350282485,
+      "grad_norm": 0.64453125,
+      "learning_rate": 0.00010348837209302327,
+      "loss": 6.255178451538086,
+      "mean_token_accuracy": 0.24344109077202647,
+      "num_tokens": 1511764.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0112994350282485,
+      "eval_entropy": 6.723124821980794,
+      "eval_loss": 6.457315921783447,
+      "eval_mean_token_accuracy": 0.20087979889164367,
+      "eval_num_tokens": 1511764.0,
+      "eval_runtime": 43.8306,
+      "eval_samples_per_second": 4.381,
+      "eval_steps_per_second": 1.095,
+      "step": 90
+    },
+    {
+      "entropy": 6.43809232711792,
+      "epoch": 1.1242937853107344,
+      "grad_norm": 0.55859375,
+      "learning_rate": 9.186046511627907e-05,
+      "loss": 6.314236068725586,
+      "mean_token_accuracy": 0.23132331417873503,
+      "num_tokens": 1682798.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.1242937853107344,
+      "eval_entropy": 6.687405467033386,
+      "eval_loss": 6.43255090713501,
+      "eval_mean_token_accuracy": 0.20094856123129526,
+      "eval_num_tokens": 1682798.0,
+      "eval_runtime": 44.0723,
+      "eval_samples_per_second": 4.356,
+      "eval_steps_per_second": 1.089,
+      "step": 100
     }
   ],
   "logging_steps": 10,
       "attributes": {}
     }
   },
+  "total_flos": 1.2023018700050227e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null