Instructions to use sravanthib/testing-without-deepspeed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sravanthib/testing-without-deepspeed with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B")
model = PeftModel.from_pretrained(base_model, "sravanthib/testing-without-deepspeed")

Transformers

How to use sravanthib/testing-without-deepspeed with Transformers:

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

pipe = pipeline("text-generation", model="sravanthib/testing-without-deepspeed")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sravanthib/testing-without-deepspeed", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sravanthib/testing-without-deepspeed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sravanthib/testing-without-deepspeed"
# 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/testing-without-deepspeed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sravanthib/testing-without-deepspeed

SGLang

How to use sravanthib/testing-without-deepspeed 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/testing-without-deepspeed" \
    --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/testing-without-deepspeed",
		"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/testing-without-deepspeed" \
        --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/testing-without-deepspeed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sravanthib/testing-without-deepspeed with Docker Model Runner:
```
docker model run hf.co/sravanthib/testing-without-deepspeed
```

sravanthib commited on Jul 14, 2025

Commit

84a5d16

verified ·

1 Parent(s): c21975f

Training completed

Browse files

Files changed (4) hide show

README.md +3 -3
all_results.json +6 -6
train_results.json +6 -6
trainer_state.json +9 -9

README.md CHANGED Viewed

@@ -37,11 +37,11 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 64
 - seed: 42
 - gradient_accumulation_steps: 10
-- total_train_batch_size: 160
 - 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

 The following hyperparameters were used during training:
 - learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 10
+- total_train_batch_size: 20
 - 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

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.0182648401826484,
-    "total_flos": 5.5657843654656e+16,
-    "train_loss": 1.3686250686645507,
-    "train_runtime": 146.0605,
-    "train_samples_per_second": 10.954,
-    "train_steps_per_second": 0.068
 }

 {
+    "epoch": 0.00228310502283105,
+    "total_flos": 6957230456832000.0,
+    "train_loss": 10.657806396484375,
+    "train_runtime": 130.9955,
+    "train_samples_per_second": 1.527,
+    "train_steps_per_second": 0.076
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.0182648401826484,
-    "total_flos": 5.5657843654656e+16,
-    "train_loss": 1.3686250686645507,
-    "train_runtime": 146.0605,
-    "train_samples_per_second": 10.954,
-    "train_steps_per_second": 0.068
 }

 {
+    "epoch": 0.00228310502283105,
+    "total_flos": 6957230456832000.0,
+    "train_loss": 10.657806396484375,
+    "train_runtime": 130.9955,
+    "train_samples_per_second": 1.527,
+    "train_steps_per_second": 0.076
 }

trainer_state.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0182648401826484,
   "eval_steps": 0,
   "global_step": 10,
   "is_hyper_param_search": false,
@@ -10,13 +10,13 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0182648401826484,
       "step": 10,
-      "total_flos": 5.5657843654656e+16,
-      "train_loss": 1.3686250686645507,
-      "train_runtime": 146.0605,
-      "train_samples_per_second": 10.954,
-      "train_steps_per_second": 0.068
     }
   ],
   "logging_steps": 100,
@@ -36,8 +36,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.5657843654656e+16,
-  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.00228310502283105,
   "eval_steps": 0,
   "global_step": 10,
   "is_hyper_param_search": false,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 0.00228310502283105,
       "step": 10,
+      "total_flos": 6957230456832000.0,
+      "train_loss": 10.657806396484375,
+      "train_runtime": 130.9955,
+      "train_samples_per_second": 1.527,
+      "train_steps_per_second": 0.076
     }
   ],
   "logging_steps": 100,
       "attributes": {}
     }
   },
+  "total_flos": 6957230456832000.0,
+  "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
 }