Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,29 +1,22 @@
 {
-  "_name_or_path": "unsloth/llama-3.2-1b-instruct-bnb-4bit",
+  "_name_or_path": "unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit",
   "architectures": [
-    "LlamaForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "head_dim": 64,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
-  "num_key_value_heads": 8,
-  "pad_token_id": 128004,
-  "pretraining_tp": 1,
+  "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": 151665,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
@@ -36,19 +29,16 @@
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float16",
   "transformers_version": "4.46.2",
-  "unsloth_version": "2024.11.6",
+  "unsloth_fixed": true,
+  "unsloth_version": "2024.11.7",
   "use_cache": true,
-  "vocab_size": 128256
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

generation_config.json

@@ -1,14 +1,15 @@
 {
-  "bos_token_id": 128000,
+  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
-    128001,
-    128008,
-    128009
+    151645,
+    151643
   ],
-  "max_length": 131072,
-  "pad_token_id": 128004,
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "max_length": 32768,
+  "pad_token_id": 151665,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494bef2055d5d3ef28e93827c9263ee4268c16ed317b76ffe2d3b1c08a532dc6
-size 1027676593
+oid sha256:43951a399196499028e6503baeb78a9a91cb02a1e2854c336bbc5aa26cd486e9
+size 457346538