Upload Qwen3ForCausalLM

config.json

@@ -4,19 +4,19 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "max_position_embeddings": 40960,
+  "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "qwen3",
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
+  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
@@ -24,6 +24,8 @@
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.5.7",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -1,13 +1,8 @@
 {
   "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "temperature": 0.6,
-  "top_k": 20,
-  "top_p": 0.95,
+  "eos_token_id": 151643,
+  "max_length": 32768,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151654,
   "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0013beb29261fb78ef2f1932eece31c07e1376794000cb11119d923330bcef1a
+oid sha256:01bc864bfdc9b4872c31b032560ef71328f506653a01ce0a8556845c04d17b34
 size 2384234968