Instructions to use mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("allenai/Llama-3.1-Tulu-3-8B")
model = PeftModel.from_pretrained(base_model, "mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara")

Transformers

How to use mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara with Transformers:

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

pipe = pipeline("text-generation", model="mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara

SGLang

How to use mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara 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 "mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara" \
    --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": "mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara",
		"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 "mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara" \
        --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": "mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara with Docker Model Runner:
```
docker model run hf.co/mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara
```

mirsazzathossain commited on May 16

Commit

4cd12fd

verified ·

1 Parent(s): 0914328

Training in progress, step 742, checkpoint

Browse files

Files changed (5) hide show

last-checkpoint/adapter_model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/rng_state.pth +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +102 -4

last-checkpoint/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234e9faba9167eb8026311e501ed98ddda9c7b01d85dc697e157b3825c672f19
 size 167832240

 version https://git-lfs.github.com/spec/v1
+oid sha256:7a4212534360d91c4750eb0488f33c9bbf9c2aa016775d2ebcf0907d221c856f
 size 167832240

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d984355f4d14d29e5f0c33d7322eaf76ca629af03d42896d42a0709d5c62e9a
 size 335922386

 version https://git-lfs.github.com/spec/v1
+oid sha256:0077ed6560805092ce34c46b5a0748dc789084a6d0c9b77d75383b2617145658
 size 335922386

last-checkpoint/rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93dfec376fcae514cc1172061dc894c88fb64c05da47049b55b9c420e46c5b6e
 size 14244

 version https://git-lfs.github.com/spec/v1
+oid sha256:b8ace2e53e972d164c5bd1d27983df1e697839e80dc6b8cb8c6d7c973b8f5b1f
 size 14244

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2d32c8942649c1bcec036a7c90f4e993d8936218dbf9a4b3743ca60e925e0b
 size 1064

 version https://git-lfs.github.com/spec/v1
+oid sha256:c10f13d9ed8b535eb36de3bf00ca4405c444905a0f35975465b1e49e824c6a21
 size 1064

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6173546756529065,
   "eval_steps": 200,
-  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -452,6 +452,104 @@
       "eval_samples_per_second": 1.825,
       "eval_steps_per_second": 1.825,
       "step": 600
     }
   ],
   "logging_steps": 10,
@@ -466,12 +564,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.903142754091008e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 2.0,
   "eval_steps": 200,
+  "global_step": 742,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 1.825,
       "eval_steps_per_second": 1.825,
       "step": 600
+    },
+    {
+      "epoch": 1.644313395113732,
+      "grad_norm": 0.3200387954711914,
+      "learning_rate": 9.49385233424856e-07,
+      "loss": 0.9581,
+      "step": 610
+    },
+    {
+      "epoch": 1.6712721145745577,
+      "grad_norm": 0.3195631504058838,
+      "learning_rate": 8.158632442673603e-07,
+      "loss": 0.9446,
+      "step": 620
+    },
+    {
+      "epoch": 1.6982308340353833,
+      "grad_norm": 0.26112768054008484,
+      "learning_rate": 6.916218039089961e-07,
+      "loss": 0.9549,
+      "step": 630
+    },
+    {
+      "epoch": 1.725189553496209,
+      "grad_norm": 0.2657977044582367,
+      "learning_rate": 5.769364838278063e-07,
+      "loss": 0.995,
+      "step": 640
+    },
+    {
+      "epoch": 1.7521482729570346,
+      "grad_norm": 0.3035813868045807,
+      "learning_rate": 4.720616597222205e-07,
+      "loss": 0.9935,
+      "step": 650
+    },
+    {
+      "epoch": 1.7791069924178602,
+      "grad_norm": 0.29046186804771423,
+      "learning_rate": 3.7722994729763427e-07,
+      "loss": 1.0067,
+      "step": 660
+    },
+    {
+      "epoch": 1.8060657118786858,
+      "grad_norm": 0.27917370200157166,
+      "learning_rate": 2.9265168631736005e-07,
+      "loss": 1.0086,
+      "step": 670
+    },
+    {
+      "epoch": 1.8330244313395114,
+      "grad_norm": 0.26591578125953674,
+      "learning_rate": 2.1851447406231573e-07,
+      "loss": 0.9478,
+      "step": 680
+    },
+    {
+      "epoch": 1.8599831508003368,
+      "grad_norm": 0.30971062183380127,
+      "learning_rate": 1.5498274923427925e-07,
+      "loss": 0.9364,
+      "step": 690
+    },
+    {
+      "epoch": 1.8869418702611624,
+      "grad_norm": 0.24184127151966095,
+      "learning_rate": 1.0219742722559433e-07,
+      "loss": 1.0085,
+      "step": 700
+    },
+    {
+      "epoch": 1.913900589721988,
+      "grad_norm": 0.32377859950065613,
+      "learning_rate": 6.027558756434015e-08,
+      "loss": 1.0718,
+      "step": 710
+    },
+    {
+      "epoch": 1.9408593091828137,
+      "grad_norm": 0.24339060485363007,
+      "learning_rate": 2.9310214228202016e-08,
+      "loss": 0.9437,
+      "step": 720
+    },
+    {
+      "epoch": 1.9678180286436393,
+      "grad_norm": 0.2631000876426697,
+      "learning_rate": 9.369989403041347e-09,
+      "loss": 0.9958,
+      "step": 730
+    },
+    {
+      "epoch": 1.994776748104465,
+      "grad_norm": 0.24943451583385468,
+      "learning_rate": 4.991411436189308e-10,
+      "loss": 0.9993,
+      "step": 740
     }
   ],
   "logging_steps": 10,
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
+  "total_flos": 6.06897586520064e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null