Trained with Unsloth

README.md

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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ehristoforu/SoRu-0004",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "unsloth_version": "2024.11.11",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15394b5f4406dd6a83b05f1e5d0d78ceaf6963329c271b7f99cf61caed76c9eb
+size 987611904