Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+base_model: HuggingFaceTB/SmolLM2-135M
 library_name: transformers
-model_name: SmolLM2-135M-Instruct_tldr-sft
+model_name: SmolLM2-135M-tldr-sft
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for SmolLM2-135M-Instruct_tldr-sft
+# Model Card for SmolLM2-135M-tldr-sft
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -20,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 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="mnoukhov/SmolLM2-135M-Instruct_tldr-sft", device="cuda")
+generator = pipeline("text-generation", model="mnoukhov/SmolLM2-135M-tldr-sft", 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/mnoukhov/bpo/runs/5586569_sft_smol135m)
+[<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/mnoukhov/bpo/runs/5586883_sft_smol135m)
 
 This model was trained with SFT.
 

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 2,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "transformers_version": "4.46.2"
 }