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", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

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 6, 2025

Commit

9e5059e

verified ·

1 Parent(s): b4f2a8d

Training completed

Browse files

Files changed (4) hide show

README.md +1 -1
all_results.json +6 -6
train_results.json +6 -6
trainer_state.json +12 -33

README.md CHANGED Viewed

@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 30
 ### Training results

 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.03
+- training_steps: 5
 ### Training results

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.0547945205479452,
-    "total_flos": 4.182326538802299e+17,
-    "train_loss": 2.981964486837387,
-    "train_runtime": 542.8101,
-    "train_samples_per_second": 8.843,
-    "train_steps_per_second": 0.055
 }

 {
+    "epoch": 0.0091324200913242,
+    "total_flos": 6.970544231337165e+16,
+    "train_loss": 11.061896514892577,
+    "train_runtime": 106.6881,
+    "train_samples_per_second": 7.498,
+    "train_steps_per_second": 0.047
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.0547945205479452,
-    "total_flos": 4.182326538802299e+17,
-    "train_loss": 2.981964486837387,
-    "train_runtime": 542.8101,
-    "train_samples_per_second": 8.843,
-    "train_steps_per_second": 0.055
 }

 {
+    "epoch": 0.0091324200913242,
+    "total_flos": 6.970544231337165e+16,
+    "train_loss": 11.061896514892577,
+    "train_runtime": 106.6881,
+    "train_samples_per_second": 7.498,
+    "train_steps_per_second": 0.047
 }

trainer_state.json CHANGED Viewed

@@ -1,49 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0547945205479452,
   "eval_steps": 0,
-  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0182648401826484,
-      "grad_norm": 10.482062339782715,
-      "learning_rate": 0.0001,
-      "loss": 8.5393,
-      "step": 10
-    },
-    {
-      "epoch": 0.0365296803652968,
-      "grad_norm": 0.1216701939702034,
-      "learning_rate": 0.0001,
-      "loss": 0.3612,
-      "step": 20
-    },
-    {
-      "epoch": 0.0547945205479452,
-      "grad_norm": 0.08138233423233032,
-      "learning_rate": 0.0001,
-      "loss": 0.0454,
-      "step": 30
-    },
-    {
-      "epoch": 0.0547945205479452,
-      "step": 30,
-      "total_flos": 4.182326538802299e+17,
-      "train_loss": 2.981964486837387,
-      "train_runtime": 542.8101,
-      "train_samples_per_second": 8.843,
-      "train_steps_per_second": 0.055
     }
   ],
   "logging_steps": 10,
-  "max_steps": 30,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 30,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -56,7 +35,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.182326538802299e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.0091324200913242,
   "eval_steps": 0,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 0.0091324200913242,
+      "step": 5,
+      "total_flos": 6.970544231337165e+16,
+      "train_loss": 11.061896514892577,
+      "train_runtime": 106.6881,
+      "train_samples_per_second": 7.498,
+      "train_steps_per_second": 0.047
     }
   ],
   "logging_steps": 10,
+  "max_steps": 5,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
+  "save_steps": 5,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
       "attributes": {}
     }
   },
+  "total_flos": 6.970544231337165e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null