Upload LlamaForCausalLM

README.md

@@ -1,14 +1,14 @@
 ---
-library_name: transformers
-tags:
-- e-commerce
-- llama3.2
-license: apache-2.0
 datasets:
 - bitext/Bitext-customer-support-llm-chatbot-training-dataset
 language:
 - en
+library_name: transformers
+license: apache-2.0
 pipeline_tag: question-answering
+tags:
+- e-commerce
+- llama3.2
 ---
 
 ## Llama-3.2-3b-it-Ecommerce-ChatBot

config.json

@@ -1,3 +1,37 @@
 {
-    "model_type": "llama"
-}
+  "_name_or_path": "/kaggle/input/llama-3.2/transformers/3b-instruct/1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128256,
+  "eos_token_id": 128257,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128257,
+  "pretraining_tp": 1,
+  "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,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 128258
+}