Upload config

README.md

@@ -1,15 +1,14 @@
 ---
 language:
 - en
-license: apache-2.0
 library_name: transformers
+license: apache-2.0
 tags:
 - unsloth
 - transformers
 - llama
 - llama2
 - llama-2
-
 ---
 
 # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "unsloth/llama-2-7b",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -12,14 +12,18 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 4096,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 2,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -34,8 +38,9 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.37.0.dev0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "vocab_size": 32000
 }