Trained with Unsloth

config.json

@@ -1,32 +1,31 @@
 {
-  "_name_or_path": "unsloth/qwen2.5-3b-bnb-4bit",
+  "_name_or_path": "unsloth/tinyllama-bnb-4bit",
   "architectures": [
-    "Qwen2ForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 36,
-  "model_type": "qwen2",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 2,
-  "pad_token_id": 151665,
-  "rms_norm_eps": 1e-06,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": true,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.44.2",
   "unsloth_version": "2024.9.post4",
   "use_cache": true,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,8 +1,7 @@
 {
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_length": 32768,
-  "max_new_tokens": 2048,
-  "pad_token_id": 151665,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.44.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2480cadeed196ef94ebe51870d768a56a87ca98ddd803d9fe371eab1b3744cbb
-size 2200164718
+oid sha256:99db162559497b1bec368379c3164798694bda8e007dba1c9d921e9bf7df1464
+size 4137933166