Upload Qwen2ForCausalLM

README.md

@@ -2,8 +2,8 @@
 language:
 - it
 - en
-license: apache-2.0
 library_name: transformers
+license: apache-2.0
 ---
 
 # Qwen2 1.5B: Almost the Same Performance as ITALIA (iGenius) but 6 Times Smaller 🚀

config.json

@@ -1,10 +1,10 @@
 {
-  "_name_or_path": "qwen_general_1.5B-DPO",
+  "_name_or_path": "Qwen_ITA",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 151644,
+  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 1536,
@@ -16,14 +16,13 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
-  "pad_token_id": 151645,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.43.0.dev0",
   "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 151646
+  "vocab_size": 151936
 }

generation_config.json

@@ -1,11 +1,14 @@
 {
-  "bos_token_id": 151644,
+  "bos_token_id": 151643,
   "do_sample": true,
-  "eos_token_id": 151645,
-  "pad_token_id": 151645,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
   "repetition_penalty": 1.1,
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.43.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d24b7fc0305fcfd87e2f428f1c2a195a9b4944c1a9e77611b891226ea6a2462
-size 3086576264
+oid sha256:43f457e34ad9e790e39325394054a7a572b0f199b50d343cfdd1926896a0fbba
+size 3087467144