Upload Qwen2ForCausalLM

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
@@ -18,13 +18,12 @@
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000,
+  "rope_theta": 1000000.0,
   "sliding_window": null,
-  "tie_word_embeddings": false,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,9 +1,14 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 151646,
+  "bos_token_id": 151643,
   "do_sample": true,
-  "eos_token_id": 151643,
-  "temperature": 0.6,
-  "top_p": 0.95,
+  "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": "4.46.1"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ad7f8d4f65c82fd60863f9e7af6fd0b23397c27164738cff5a867981e827e57
+oid sha256:84ddf070d6d38cb6f8ad1a522a66aef753c7eb8ad92dc916103d277f14a0f1a6
 size 4996670464

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037a96b27ac10bdb40e3b5457961a1da70a0d4652dcdcf40dc5c814244908126
-size 2111719976
+oid sha256:3d7c6a0fa6b00809bb7e01e83f6a9b2cd9ccbbe5d717408a829affdd465a2104
+size 1178224960

model.safetensors.index.json

@@ -1,9 +1,8 @@
 {
   "metadata": {
-    "total_size": 7108352000
+    "total_size": 6174857216
   },
   "weight_map": {
-    "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",