Instructions to use SystemAdmin123/tiny-random-LlamaForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SystemAdmin123/tiny-random-LlamaForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="SystemAdmin123/tiny-random-LlamaForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SystemAdmin123/tiny-random-LlamaForCausalLM")
model = AutoModelForCausalLM.from_pretrained("SystemAdmin123/tiny-random-LlamaForCausalLM")
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 SystemAdmin123/tiny-random-LlamaForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SystemAdmin123/tiny-random-LlamaForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/tiny-random-LlamaForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SystemAdmin123/tiny-random-LlamaForCausalLM

SGLang

How to use SystemAdmin123/tiny-random-LlamaForCausalLM 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 "SystemAdmin123/tiny-random-LlamaForCausalLM" \
    --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": "SystemAdmin123/tiny-random-LlamaForCausalLM",
		"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 "SystemAdmin123/tiny-random-LlamaForCausalLM" \
        --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": "SystemAdmin123/tiny-random-LlamaForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SystemAdmin123/tiny-random-LlamaForCausalLM with Docker Model Runner:
```
docker model run hf.co/SystemAdmin123/tiny-random-LlamaForCausalLM
```

SystemAdmin123 commited on Feb 6, 2025

Commit

6be4b7c

verified ·

1 Parent(s): 8c6811a

Training in progress, step 150, checkpoint

Browse files

Files changed (6) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/rng_state_0.pth +1 -1
last-checkpoint/rng_state_1.pth +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +46 -3

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c2ecd92e57b2e66ca22969473f53cb6e090828806462e132c671e6e2d3f419
 size 2066752

 version https://git-lfs.github.com/spec/v1
+oid sha256:a53818166c997a5f044919047269de5637df30c7f3e35e43de5a49620a745bac
 size 2066752

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b8912999820c91e1c8c8c8687a2636c8a6f4f493c6ac56b50cf98a74706856
 size 2162798

 version https://git-lfs.github.com/spec/v1
+oid sha256:28dd6e6307fa015e692b6b556932fde5666659c25197be0bf989d11c190341f1
 size 2162798

last-checkpoint/rng_state_0.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddb8fcdae8dea7e10388731f63246ec0494e51d6d509273113166b14d83f0e3
 size 14512

 version https://git-lfs.github.com/spec/v1
+oid sha256:6371144a111a3072f591f746239d824c555a871e29310d8421824db33cb69d80
 size 14512

last-checkpoint/rng_state_1.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24238ca2ad5e52c7a2d983c253be8a0ab25f258c2785c7ba56c4bfa08fb89d84
 size 14512

 version https://git-lfs.github.com/spec/v1
+oid sha256:2bc12850c9ff9801525024d9966df4799da11201038cba4971a720ddadfcd7ec
 size 14512

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
 size 1064

 version https://git-lfs.github.com/spec/v1
+oid sha256:bb0e11d33e42a9adcc5c976e37e059307e91eb6ae74c969ff1b3eb2f755782d6
 size 1064

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.6923076923076925,
   "eval_steps": 50,
-  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 284.164,
       "eval_steps_per_second": 4.544,
       "step": 100
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 40915854950400.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 11.538461538461538,
   "eval_steps": 50,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 284.164,
       "eval_steps_per_second": 4.544,
       "step": 100
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00019043571606975777,
+      "loss": 9.942,
+      "step": 110
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 9.8887,
+      "step": 120
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00018519194088383273,
+      "loss": 9.836,
+      "step": 130
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.0001821777815225245,
+      "loss": 9.7845,
+      "step": 140
+    },
+    {
+      "epoch": 11.538461538461538,
+      "grad_norm": 0.361328125,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 9.7359,
+      "step": 150
+    },
+    {
+      "epoch": 11.538461538461538,
+      "eval_loss": 9.719038963317871,
+      "eval_runtime": 5.2736,
+      "eval_samples_per_second": 284.626,
+      "eval_steps_per_second": 4.551,
+      "step": 150
     }
   ],
   "logging_steps": 10,
       "attributes": {}
     }
   },
+  "total_flos": 61373782425600.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null