Upload Qwen2ForCausalLM

config.json

@@ -17,26 +17,11 @@
   "num_hidden_layers": 24,
   "num_key_value_heads": 16,
   "pad_token_id": 151645,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
-    "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"
-  },
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.40.2",
   "use_cache": true,
   "use_sliding_window": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f0354da4f18b31b50899f922482ede471ac071d0d665a4e2ed6b677a4cf4ff
-size 3134844532
+oid sha256:3890b526292709f739445489bd50d6891f4685ee4a241e3728291e0c5af9d89d
+size 3671314720