Trained with Unsloth

README.md

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - qwen2
 - trl
+- sft
 license: apache-2.0
 language:
 - en

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "KingNish/depth20-qwen-1b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 6452,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 23,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "unsloth_version": "2025.3.8",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_length": 131072,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151654,
+  "transformers_version": "4.48.3"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c59b90c22ae24a03273cdb3faea17a3a8378eb6d4c50d2dc65ff7f295ca7bf
+size 2554675814