Upload Qwen2ForCausalLM

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -19,10 +18,10 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,
-  "sliding_window": null,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.51.3",
   "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 151643,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.48.3"
+  "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981c000e58fb26ae762dd2050adbfd7cfcca6d97476e9fc92fd4f921adae8e47
-size 3087465120
+oid sha256:8f929f4b331971a962757c995839ed59af9fa5b67d7bea59435483a032e59c93
+size 3554214752