Training in progress, step 50

README.md

@@ -1,22 +1,59 @@
 ---
 base_model: unsloth/LFM2.5-1.2B-Instruct
+library_name: transformers
+model_name: actor_alignments
 tags:
-- text-generation-inference
-- transformers
+- generated_from_trainer
+- sft
 - unsloth
-- lfm2
 - trl
-license: apache-2.0
-language:
-- en
+licence: license
 ---
 
-# Uploaded  model
+# Model Card for actor_alignments
 
-- **Developed by:** ktcapraz
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/LFM2.5-1.2B-Instruct
+This model is a fine-tuned version of [unsloth/LFM2.5-1.2B-Instruct](https://huggingface.co/unsloth/LFM2.5-1.2B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-This lfm2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
+## Quick start
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+```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="ktcapraz/actor_alignments", 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: 0.22.2
+- Transformers: 4.57.3
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## 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 Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -33,14 +33,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "w1",
-    "in_proj",
+    "out_proj",
     "w2",
+    "w3",
     "q_proj",
-    "k_proj",
-    "out_proj",
-    "w3"
+    "in_proj",
+    "v_proj",
+    "w1",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14e44ee95c3ff008e00f77ee17fd44a66d9ce66be8068be0e38e0bd3dddb8d3
+oid sha256:5736c925db7f325caa64064fa8c0c51ab5fa9a598482c0300d3b977751127823
 size 44457856

tokenizer_config.json

@@ -4086,7 +4086,7 @@
   ],
   "model_max_length": 128000,
   "pad_token": "<|pad|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688a6761a22b79afbe6742b918b8c7c5ea39cbbdc735735112f8fe014a9713b7
+size 6353