Upload Qwen2ForCausalLM

config.json

@@ -1,29 +1,30 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 896,
+  "hidden_size": 1536,
   "initializer_range": 0.02,
-  "intermediate_size": 4864,
-  "max_position_embeddings": 32768,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
   "max_window_layers": 21,
   "model_type": "qwen2",
-  "num_attention_heads": 14,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
+  "rope_theta": 10000,
   "sliding_window": null,
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.47.0",
   "use_cache": true,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,14 +1,9 @@
 {
-  "bos_token_id": 151643,
+  "_from_model_config": true,
+  "bos_token_id": 151646,
   "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
   "transformers_version": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72409d6b0e77d44835d227d2672a8eaccaf438886ef03420578eb2f17b87e181
-size 988097536
+oid sha256:c81e38cd4bfd5d7ffae365b6d1872270f5960639258e842ffaccb217e8ad17a8
+size 3554214416