Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: transformers
+model_name: Llama-3.2-3B-Instruct-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Llama-3.2-3B-Instruct-Open-R1-Distill
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="ItsMaxNorm/Llama-3.2-3B-Instruct-Open-R1-Distill", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+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/cvmi-research/huggingface/runs/st9taf87) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.14.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.99608457321848,
+    "total_flos": 1.3245374097522688e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.8638,
+    "train_samples": 25371,
+    "train_samples_per_second": 54818.89,
+    "train_steps_per_second": 855.791
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.49.0.dev0"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.99608457321848,
+    "total_flos": 1.3245374097522688e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.8638,
+    "train_samples": 25371,
+    "train_samples_per_second": 54818.89,
+    "train_steps_per_second": 855.791
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc46d19a66d82c9211f0719b2f32d11a404912eff88c82df531557d618aabec
+oid sha256:275e99c9cc5c524d125d01a88c2efb913c7b5a190c7853486150f08c347aeaf2
 size 7672