Instructions to use harsha070/expfinal-phi-mbpp-s42-lambda-0p0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use harsha070/expfinal-phi-mbpp-s42-lambda-0p0 with Transformers:

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

pipe = pipeline("text-generation", model="harsha070/expfinal-phi-mbpp-s42-lambda-0p0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("harsha070/expfinal-phi-mbpp-s42-lambda-0p0", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("harsha070/expfinal-phi-mbpp-s42-lambda-0p0", trust_remote_code=True)
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 Settings

vLLM

How to use harsha070/expfinal-phi-mbpp-s42-lambda-0p0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "harsha070/expfinal-phi-mbpp-s42-lambda-0p0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harsha070/expfinal-phi-mbpp-s42-lambda-0p0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/harsha070/expfinal-phi-mbpp-s42-lambda-0p0

SGLang

How to use harsha070/expfinal-phi-mbpp-s42-lambda-0p0 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 "harsha070/expfinal-phi-mbpp-s42-lambda-0p0" \
    --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": "harsha070/expfinal-phi-mbpp-s42-lambda-0p0",
		"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 "harsha070/expfinal-phi-mbpp-s42-lambda-0p0" \
        --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": "harsha070/expfinal-phi-mbpp-s42-lambda-0p0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use harsha070/expfinal-phi-mbpp-s42-lambda-0p0 with Docker Model Runner:
```
docker model run hf.co/harsha070/expfinal-phi-mbpp-s42-lambda-0p0
```

harsha070 commited on about 1 month ago

Commit

3064a20

verified ·

1 Parent(s): 6851022

Training in progress, step 140, checkpoint

Browse files

Files changed (2) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/trainer_state.json +32 -4

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:212db1c26305411a7481f2d8ce83d1de464611483b3d2a7e0073511a9a28bd50
 size 7642181896

 version https://git-lfs.github.com/spec/v1
+oid sha256:9b2557098ef4b87535e5e0fd4378a8cf45a8b75aabf3a08c3cd2adb53c632e4d
 size 7642181896

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8666666666666667,
   "eval_steps": 500,
-  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -372,11 +372,39 @@
       "rewards/JointRewardFunction/std": 0.24954410195350646,
       "step": 130,
       "step_time": 18.954484624400358
     }
   ],
   "logging_steps": 10,
   "max_steps": 140,
-  "num_input_tokens_seen": 669175,
   "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {
@@ -386,7 +414,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
       },
       "attributes": {}
     }

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.9333333333333333,
   "eval_steps": 500,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "rewards/JointRewardFunction/std": 0.24954410195350646,
       "step": 130,
       "step_time": 18.954484624400358
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.65,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 358.6,
+      "completions/mean_length": 460.2875,
+      "completions/mean_terminated_length": 291.386669921875,
+      "completions/min_length": 324.7,
+      "completions/min_terminated_length": 222.3,
+      "entropy": 0.27632327415049074,
+      "epoch": 0.9333333333333333,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.00445556640625,
+      "kl": 0.03374400998000056,
+      "learning_rate": 7.142857142857144e-08,
+      "loss": 0.00835585966706276,
+      "num_tokens": 720794.0,
+      "reward": 0.925,
+      "reward_std": 0.1632926881313324,
+      "rewards/JointRewardFunction/mean": 0.925,
+      "rewards/JointRewardFunction/std": 0.1632926881313324,
+      "step": 140,
+      "step_time": 18.98217402150076
     }
   ],
   "logging_steps": 10,
   "max_steps": 140,
+  "num_input_tokens_seen": 720794,
   "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
+        "should_training_stop": true
       },
       "attributes": {}
     }