Instructions to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with Transformers:

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

pipe = pipeline("text-generation", model="rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean")
model = AutoModelForCausalLM.from_pretrained("rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean")
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

vLLM

How to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean

SGLang

How to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean 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 "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean" \
    --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": "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean",
		"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 "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean" \
        --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": "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with Docker Model Runner:
```
docker model run hf.co/rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
```

rkumar1999 commited on Mar 3, 2025

Commit

d9e8e8f

verified ·

1 Parent(s): e2fe931

Model save

Browse files

Files changed (8) hide show

README.md +2 -4
adapter_config.json +2 -2
adapter_model.safetensors +1 -1
all_results.json +5 -5
runs/Mar03_21-17-14_ip-10-192-12-214/events.out.tfevents.1741036644.ip-10-192-12-214.31425.0 +3 -0
train_results.json +5 -5
trainer_state.json +9 -9
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,11 +1,9 @@
 ---
 base_model: meta-llama/Llama-3.1-8B-Instruct
-datasets: Tonic/MiniF2F
 library_name: transformers
 model_name: Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 # Model Card for Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the [Tonic/MiniF2F](https://huggingface.co/datasets/Tonic/MiniF2F) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rohanbayya1205-san-jose-state-university/huggingface/runs/ws8rmwff)
 This model was trained with SFT.

 ---
 base_model: meta-llama/Llama-3.1-8B-Instruct
 library_name: transformers
 model_name: Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
 tags:
 - generated_from_trainer
 - trl
 - sft
 licence: license
 # Model Card for Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rohanbayya1205-san-jose-state-university/huggingface/runs/rl8xdbu7)
 This model was trained with SFT.

adapter_config.json CHANGED Viewed

@@ -24,9 +24,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

   "revision": null,
   "target_modules": [
     "o_proj",
+    "q_proj",
     "k_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9b528d33a706136dec74218a64d50402715fa9285eb6f9d674a1b99a1184e5
 size 7522752

 version https://git-lfs.github.com/spec/v1
+oid sha256:d80adfc6a5efc9cfe88bcdaf9fee15d1da4c8e085b7b344176dd37d21f39eb80
 size 7522752

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "total_flos": 196696080384.0,
-    "train_loss": 3363.7795448303223,
-    "train_runtime": 10.1807,
     "train_samples": 488,
-    "train_samples_per_second": 1.768,
-    "train_steps_per_second": 0.196
 }

 {
+    "total_flos": 3737225527296.0,
+    "train_loss": 33168.128967285156,
+    "train_runtime": 78.7129,
     "train_samples": 488,
+    "train_samples_per_second": 2.287,
+    "train_steps_per_second": 0.254
 }

runs/Mar03_21-17-14_ip-10-192-12-214/events.out.tfevents.1741036644.ip-10-192-12-214.31425.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:df0ca1acb1f86d1f3e1d89675ba8a6f99f2ab6dfcd414fad91a483b8e19a063b
+size 6506

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "total_flos": 196696080384.0,
-    "train_loss": 3363.7795448303223,
-    "train_runtime": 10.1807,
     "train_samples": 488,
-    "train_samples_per_second": 1.768,
-    "train_steps_per_second": 0.196
 }

 {
+    "total_flos": 3737225527296.0,
+    "train_loss": 33168.128967285156,
+    "train_runtime": 78.7129,
     "train_samples": 488,
+    "train_samples_per_second": 2.287,
+    "train_steps_per_second": 0.254
 }

trainer_state.json CHANGED Viewed

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 0,
-      "mean_token_accuracy": 0.6600732803344727,
       "step": 0,
-      "total_flos": 196696080384.0,
-      "train_loss": 3363.7795448303223,
-      "train_runtime": 10.1807,
-      "train_samples_per_second": 1.768,
-      "train_steps_per_second": 0.196
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -36,7 +36,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 196696080384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

   "log_history": [
     {
       "epoch": 0,
+      "mean_token_accuracy": 0.6642943471670151,
       "step": 0,
+      "total_flos": 3737225527296.0,
+      "train_loss": 33168.128967285156,
+      "train_runtime": 78.7129,
+      "train_samples_per_second": 2.287,
+      "train_steps_per_second": 0.254
     }
   ],
   "logging_steps": 500,
+  "max_steps": 20,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
       "attributes": {}
     }
   },
+  "total_flos": 3737225527296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d9addc654a14dc4841e1d019ae713ceb25955f72671e8521e85905de27bf43
 size 7352

 version https://git-lfs.github.com/spec/v1
+oid sha256:fe6a1413db8bfaa2c249f4c9a06e39b05fc03a29e90894f1e1a020a801111c97
 size 7352