Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: HuggingFaceTB/SmolVLM-256M-Instruct
+library_name: transformers
+model_name: SmolVLM-256M-Instruct-SFT-CLEVR
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for SmolVLM-256M-Instruct-SFT-CLEVR
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolVLM-256M-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-256M-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="theevolutionisnear/SmolVLM-256M-Instruct-SFT-CLEVR", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.0
+- Transformers: 4.47.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.0.2
+- 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}}
+}
+```

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019b2bac83536dae990e843ff67f230e937084cb966719f9083dc8350bdb4194
+oid sha256:a8cbd3cafc6dbb4086d00cf7c427e0ba3301fbe5b0c87b94b9f18e50bcceee80
 size 11608320

runs/Mar04_12-18-32_f8c7b515f676/events.out.tfevents.1741090722.f8c7b515f676.31.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf1df6df4820e852f29e1c66eb55eea7d913cfdec12a8d75d0f7aac1a739fc5
-size 14966
+oid sha256:74b7a3b110754bcb5ed320cbd81d742aaf61ff53929a19ba537a753fc01fd9d3
+size 15320

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Left",
+    "max_length": 8192,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": {
     "strategy": "BatchLongest",
     "direction": "Right",