Upload Qwen3ForCausalLM

config.json

@@ -4,7 +4,8 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "dtype": "float16",
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -55,28 +56,15 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 36,
   "num_key_value_heads": 8,
-  "pad_token_id": 151643,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
+  "pad_token_id": null,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 5000000,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "4.57.3",
+  "transformers_version": "5.4.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -1,4 +1,5 @@
 {
+  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
@@ -8,5 +9,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.57.3"
+  "transformers_version": "5.4.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e4aa00ee0daec74f4af4a7ede267db0205d7abdb3fced379ce74e326cc9bf9
-size 2653133484
+oid sha256:585c8007efce52fc64561aee415fcc61a5261eac275f973f90be16cc7e8aabd3
+size 8044982080