Upload LlamaForCausalLM

README.md

@@ -1,14 +1,13 @@
 ---
 language:
 - en
-license: apache-2.0
 library_name: transformers
+license: apache-2.0
 tags:
 - unsloth
 - transformers
 - codellama
 - codellama-7b
-
 ---
 
 # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

config.json

@@ -12,16 +12,17 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 16384,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "quantization_config": {
     "_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,
@@ -37,7 +38,7 @@
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.0.dev0",
+  "transformers_version": "4.43.3",
   "use_cache": true,
   "vocab_size": 32016
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.43.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d636d5f7fa4ffdf7524d90a772e5db520e3a96be9f4003e78693c41788a4325
-size 3866304243
+oid sha256:77c6ef940402724bd88cd1043177aae981e269badc0dac59847e29097a26810c
+size 3866304467