Instructions to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B")
model = AutoModelWithLMHead.from_pretrained("OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B

SGLang

How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B 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 "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B" \
    --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": "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B",
		"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 "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B" \
        --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": "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with Docker Model Runner:
```
docker model run hf.co/OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B
```

OsamaMo commited on Mar 6, 2025

Commit

89e6d1d

verified ·

1 Parent(s): 9864f98

Training in progress, step 500, checkpoint

Browse files

Files changed (3) hide show

last-checkpoint/adapter_config.json +4 -4
last-checkpoint/trainer_state.json +15 -15
last-checkpoint/training_args.bin +1 -1

last-checkpoint/adapter_config.json CHANGED Viewed

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
-    "down_proj",
-    "gate_proj",
     "q_proj",
     "v_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
     "v_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -81,9 +81,9 @@
     {
       "epoch": 0.07145409074669525,
       "eval_news_finetune_val_loss": 0.48679304122924805,
-      "eval_news_finetune_val_runtime": 1002.7224,
-      "eval_news_finetune_val_samples_per_second": 1.396,
-      "eval_news_finetune_val_steps_per_second": 1.396,
       "step": 100
     },
     {
@@ -159,9 +159,9 @@
     {
       "epoch": 0.1429081814933905,
       "eval_news_finetune_val_loss": 0.4338369369506836,
-      "eval_news_finetune_val_runtime": 1003.2801,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
       "step": 200
     },
     {
@@ -237,9 +237,9 @@
     {
       "epoch": 0.21436227224008575,
       "eval_news_finetune_val_loss": 0.40391305088996887,
-      "eval_news_finetune_val_runtime": 1003.2872,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
       "step": 300
     },
     {
@@ -315,9 +315,9 @@
     {
       "epoch": 0.285816362986781,
       "eval_news_finetune_val_loss": 0.39322975277900696,
-      "eval_news_finetune_val_runtime": 1003.4166,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
       "step": 400
     },
     {
@@ -393,9 +393,9 @@
     {
       "epoch": 0.35727045373347627,
       "eval_news_finetune_val_loss": 0.3787713646888733,
-      "eval_news_finetune_val_runtime": 1003.589,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
       "step": 500
     }
   ],

     {
       "epoch": 0.07145409074669525,
       "eval_news_finetune_val_loss": 0.48679304122924805,
+      "eval_news_finetune_val_runtime": 1001.9158,
+      "eval_news_finetune_val_samples_per_second": 1.397,
+      "eval_news_finetune_val_steps_per_second": 1.397,
       "step": 100
     },
     {
     {
       "epoch": 0.1429081814933905,
       "eval_news_finetune_val_loss": 0.4338369369506836,
+      "eval_news_finetune_val_runtime": 1002.1695,
+      "eval_news_finetune_val_samples_per_second": 1.397,
+      "eval_news_finetune_val_steps_per_second": 1.397,
       "step": 200
     },
     {
     {
       "epoch": 0.21436227224008575,
       "eval_news_finetune_val_loss": 0.40391305088996887,
+      "eval_news_finetune_val_runtime": 1002.5797,
+      "eval_news_finetune_val_samples_per_second": 1.396,
+      "eval_news_finetune_val_steps_per_second": 1.396,
       "step": 300
     },
     {
     {
       "epoch": 0.285816362986781,
       "eval_news_finetune_val_loss": 0.39322975277900696,
+      "eval_news_finetune_val_runtime": 1002.8865,
+      "eval_news_finetune_val_samples_per_second": 1.396,
+      "eval_news_finetune_val_steps_per_second": 1.396,
       "step": 400
     },
     {
     {
       "epoch": 0.35727045373347627,
       "eval_news_finetune_val_loss": 0.3787713646888733,
+      "eval_news_finetune_val_runtime": 1002.8588,
+      "eval_news_finetune_val_samples_per_second": 1.396,
+      "eval_news_finetune_val_steps_per_second": 1.396,
       "step": 500
     }
   ],

last-checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2782bf8a609c154eefb42753d138dafcba3aa0ea92b9d87f5184a3cbc4f0f0be
 size 5624

 version https://git-lfs.github.com/spec/v1
+oid sha256:367406c6dccce148fee91e86e6fa08ac415e3c6a88231b8f42f8d49575bf98f6
 size 5624