Trained with Unsloth

README.md

@@ -6,6 +6,8 @@ datasets:
 - 0xZee/dataset-CoT-Space-Physics-Astrophysics-76
 tags:
 - unsloth
+- trl
+- sft
 ---
 
 # Finetunning deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on 0xZee/dataset-CoT-Physics-Astrophysics

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "unsloth/deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.2.4",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_length": 131072,
+  "pad_token_id": 151654,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.48.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b773745ee2aad94baff9d075f066d7f0582eebb5fbf727d37ecec93b8667b3
+size 3554290006