Trained with Unsloth

config.json

@@ -1,30 +1,31 @@
 {
-  "_name_or_path": "unsloth/gemma-7b-bnb-4bit",
+  "_name_or_path": "unsloth/tinyllama-bnb-4bit",
   "architectures": [
-    "GemmaForCausalLM"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "head_dim": 256,
-  "hidden_act": "gelu",
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3072,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 24576,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 16,
+  "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,
-  "rms_norm_eps": 1e-06,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.4",
   "unsloth_version": "2024.7",
   "use_cache": true,
-  "vocab_size": 256000
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
   "pad_token_id": 0,
   "transformers_version": "4.42.4"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4591b5251954f662065e0bdc643096d67ec0417c75c2f87805fe8e2c4fa44dcf
+size 2200119864