Instructions to use sravanthib/qwen_model_testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sravanthib/qwen_model_testing with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-7B")
model = PeftModel.from_pretrained(base_model, "sravanthib/qwen_model_testing")

Transformers

How to use sravanthib/qwen_model_testing with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sravanthib/qwen_model_testing", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sravanthib/qwen_model_testing with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sravanthib/qwen_model_testing

SGLang

How to use sravanthib/qwen_model_testing 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 "sravanthib/qwen_model_testing" \
    --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": "sravanthib/qwen_model_testing",
		"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 "sravanthib/qwen_model_testing" \
        --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": "sravanthib/qwen_model_testing",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sravanthib/qwen_model_testing with Docker Model Runner:
```
docker model run hf.co/sravanthib/qwen_model_testing
```

sravanthib commited on Jul 11, 2025

Commit

15f4c1c

verified ·

1 Parent(s): 1e77c97

Training completed

Browse files

Files changed (4) hide show

README.md +1 -1
all_results.json +5 -5
train_results.json +5 -5
trainer_state.json +14 -7

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 160
 - total_eval_batch_size: 64
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
 - training_steps: 10

 - total_train_batch_size: 160
 - total_eval_batch_size: 64
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.03
 - training_steps: 10

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0182648401826484,
-    "total_flos": 8.713180396545638e+16,
-    "train_loss": 9.561991882324218,
-    "train_runtime": 174.8934,
-    "train_samples_per_second": 9.148,
-    "train_steps_per_second": 0.057
 }

 {
     "epoch": 0.0182648401826484,
+    "total_flos": 1.394108846267433e+17,
+    "train_loss": 5.07354736328125,
+    "train_runtime": 154.4303,
+    "train_samples_per_second": 10.361,
+    "train_steps_per_second": 0.065
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0182648401826484,
-    "total_flos": 8.713180396545638e+16,
-    "train_loss": 9.561991882324218,
-    "train_runtime": 174.8934,
-    "train_samples_per_second": 9.148,
-    "train_steps_per_second": 0.057
 }

 {
     "epoch": 0.0182648401826484,
+    "total_flos": 1.394108846267433e+17,
+    "train_loss": 5.07354736328125,
+    "train_runtime": 154.4303,
+    "train_samples_per_second": 10.361,
+    "train_steps_per_second": 0.065
 }

trainer_state.json CHANGED Viewed

@@ -9,17 +9,24 @@
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0182648401826484,
       "step": 10,
-      "total_flos": 8.713180396545638e+16,
-      "train_loss": 9.561991882324218,
-      "train_runtime": 174.8934,
-      "train_samples_per_second": 9.148,
-      "train_steps_per_second": 0.057
     }
   ],
-  "logging_steps": 50,
   "max_steps": 10,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
@@ -36,7 +43,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.713180396545638e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.0182648401826484,
+      "grad_norm": 0.36667829751968384,
+      "learning_rate": 0.0001,
+      "loss": 5.0735,
+      "step": 10
+    },
     {
       "epoch": 0.0182648401826484,
       "step": 10,
+      "total_flos": 1.394108846267433e+17,
+      "train_loss": 5.07354736328125,
+      "train_runtime": 154.4303,
+      "train_samples_per_second": 10.361,
+      "train_steps_per_second": 0.065
     }
   ],
+  "logging_steps": 10,
   "max_steps": 10,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
       "attributes": {}
     }
   },
+  "total_flos": 1.394108846267433e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null