Upload Qwen2ForCausalLM

config.json

@@ -1,10 +1,9 @@
 {
-  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
+  "bos_token_id": 151646,
   "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 3584,
@@ -16,13 +15,30 @@
   "num_attention_heads": 28,
   "num_hidden_layers": 28,
   "num_key_value_heads": 4,
+  "pad_token_id": 151654,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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"
+  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.2",
+  "unsloth_fixed": true,
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

generation_config.json

@@ -3,7 +3,9 @@
   "bos_token_id": 151646,
   "do_sample": true,
   "eos_token_id": 151643,
+  "max_length": 131072,
+  "pad_token_id": 151654,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.50.2"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917ae331c52b63e90102f91ea6880678227e35e09fd8a20e2a3617dcfc3110fd
+size 4761275200

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb5bfd8d83c32acc68b6291e53f9af6d846c2faeb0d2b36310e6fa69cc9d6d43
+size 1089994880