Upload Qwen2ForCausalLM

config.json

@@ -1,30 +1,29 @@
 {
-  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "_name_or_path": "Qwen/Qwen2.5-Coder-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_window_layers": 21,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "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": "bfloat16",
   "transformers_version": "4.47.0",
   "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": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bea0a35dba47a078ac1750e001512a02837da37c70c3c806244efbe9efefc8
-size 3554214752
+oid sha256:c1b9b30e907950516ba3c646bdf570d8084c25a6410a0cdca80cf04b11bc13a8
+size 3087467144