Trained with Unsloth

config.json

@@ -1,30 +1,35 @@
 {
-  "_name_or_path": "unsloth/phi-3-mini-4k-instruct-bnb-4bit",
+  "_name_or_path": "unsloth/tinyllama-chat-bnb-4bit",
   "architectures": [
-    "MistralForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "head_dim": 96,
+  "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 3072,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
+  "intermediate_size": 5632,
   "max_position_embeddings": 4096,
-  "model_type": "mistral",
+  "mlp_bias": false,
+  "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pad_token_id": 32009,
+  "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_scaling": {
+    "factor": 2.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
   "rope_theta": 10000.0,
-  "sliding_window": 2048,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.44.0",
   "unsloth_version": "2024.8",
   "use_cache": true,
-  "vocab_size": 32064
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,12 +1,7 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": [
-    32000,
-    32001,
-    32007
-  ],
+  "eos_token_id": 2,
   "max_length": 4096,
-  "pad_token_id": 32009,
+  "pad_token_id": 0,
   "transformers_version": "4.44.0"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e273005e98bc640bedd4ed7752afe283e6f8f47174c767f011f5261587c463
+size 2200164718