Training in progress, step 250

README.md

@@ -1,3 +1,58 @@
 ---
-license: cc-by-nc-4.0
+base_model: LiquidAI/LFM2.5-1.2B-Thinking
+library_name: transformers
+model_name: lfm-2.5-think-code
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
 ---
+
+# Model Card for lfm-2.5-think-code
+
+This model is a fine-tuned version of [LiquidAI/LFM2.5-1.2B-Thinking](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking).
+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="enseven/lfm-2.5-think-code", 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/e23bcau0045-bennett-university/lfm25-kodcode/runs/8tz1n3sx) 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.9.0
+- Transformers: 5.14.1
+- Pytorch: 2.10.0+cu128
+- Datasets: 5.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -30,15 +30,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
-    "w2",
+    "o_proj",
     "w3",
     "v_proj",
-    "k_proj",
+    "w1",
+    "w2",
     "q_proj",
+    "k_proj",
     "in_proj",
-    "w1",
-    "o_proj"
+    "out_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0b61df776369abde888bf8e917aff9409efff2a408fc8de4f4851681bbe2ff
-size 88891320
+oid sha256:34ff8b858574d48b103bd046ada2cdc96ba364ff870bad5da9cd6583dab02e9a
+size 44458040

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be508886cd187b77d2df7d207adc5ee7e63ad4c8437c47b158efc4bdd998d08
-size 5521
+oid sha256:06dc8a62efd1d9c723956615b41c7dcee7c7ac98f02c0c894936b33b95d63ecf
+size 5841