Instructions to use SystemAdmin123/llama-68m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SystemAdmin123/llama-68m with Transformers:

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

pipe = pipeline("text-generation", model="SystemAdmin123/llama-68m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SystemAdmin123/llama-68m")
model = AutoModelForCausalLM.from_pretrained("SystemAdmin123/llama-68m")
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/llama-68m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SystemAdmin123/llama-68m"
# 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/llama-68m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SystemAdmin123/llama-68m

SGLang

How to use SystemAdmin123/llama-68m 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/llama-68m" \
    --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/llama-68m",
		"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/llama-68m" \
        --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/llama-68m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SystemAdmin123/llama-68m with Docker Model Runner:
```
docker model run hf.co/SystemAdmin123/llama-68m
```

SystemAdmin123 commited on Feb 6, 2025

Commit

9a56763

verified ·

1 Parent(s): bd1996e

Training in progress, step 600, 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 +47 -4

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb5510d1b55f44ce0aad6fca441bbd65fd2fcbf55153ec23422d5bfa442e83c
 size 136062744

 version https://git-lfs.github.com/spec/v1
+oid sha256:463e50976fdd4523d72dfa1f9dde00e7d2fb94044b71ff95fa42ebac380383f9
 size 136062744

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c47860f969d19f1732995ffddb49a5f9ba7e408d1dd376ecac4a2b77aeec61f
 size 138234066

 version https://git-lfs.github.com/spec/v1
+oid sha256:0622f360da035ed6f191ceef1a70160b2b4f027c1bb245098847e56aae470e88
 size 138234066

last-checkpoint/rng_state_0.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d51e4a7056c3558a387ed54a4d13c51368f1e567102a0ee859969fb5f31cd3
 size 14512

 version https://git-lfs.github.com/spec/v1
+oid sha256:da2a7e5837e8166f34d69c47cbcb9c5f754b8d9aaee67ec69e6f2fe466d72356
 size 14512

last-checkpoint/rng_state_1.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1204ca9be37de89665f7f1742f206de4543c6c56db448f2a4968fb174cdf1393
 size 14512

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd3708ae31f1069fc45ac5848423f03f6df0cd0e16b6138df98e3ba73d336476
 size 14512

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0160b3598707f8907336269c674f5ce56b2bbdea80b3e53648f4959f2a4937ca
 size 1064

 version https://git-lfs.github.com/spec/v1
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 42.30769230769231,
   "eval_steps": 50,
-  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -488,6 +488,49 @@
       "eval_samples_per_second": 265.392,
       "eval_steps_per_second": 4.243,
       "step": 550
     }
   ],
   "logging_steps": 10,
@@ -502,12 +545,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.87955788382208e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 46.15384615384615,
   "eval_steps": 50,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 265.392,
       "eval_steps_per_second": 4.243,
       "step": 550
+    },
+    {
+      "epoch": 43.07692307692308,
+      "grad_norm": 0.61328125,
+      "learning_rate": 2.420361737256438e-06,
+      "loss": 0.6671,
+      "step": 560
+    },
+    {
+      "epoch": 43.84615384615385,
+      "grad_norm": 0.62890625,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.6683,
+      "step": 570
+    },
+    {
+      "epoch": 44.61538461538461,
+      "grad_norm": 0.59375,
+      "learning_rate": 6.069322682050516e-07,
+      "loss": 0.6714,
+      "step": 580
+    },
+    {
+      "epoch": 45.38461538461539,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.518483566683826e-07,
+      "loss": 0.6695,
+      "step": 590
+    },
+    {
+      "epoch": 46.15384615384615,
+      "grad_norm": 0.62109375,
+      "learning_rate": 0.0,
+      "loss": 0.6667,
+      "step": 600
+    },
+    {
+      "epoch": 46.15384615384615,
+      "eval_loss": 4.010259628295898,
+      "eval_runtime": 5.6787,
+      "eval_samples_per_second": 264.32,
+      "eval_steps_per_second": 4.226,
+      "step": 600
     }
   ],
   "logging_steps": 10,
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
+  "total_flos": 2.05042678235136e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null