Upload LlamaForCausalLM

config.json

@@ -16,24 +16,12 @@
   "num_key_value_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float32",
-    "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": false,
-    "load_in_8bit": true,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.34.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:804fff7b7be527f0702c9e36c0f56f50389a757743f6b6178c8f6278a13cf029
-size 9976623130
+oid sha256:1db75eeaf411b6abc2a7b124803f122560a8afd8fe363746d8bd800aa859da7c
+size 9976620122

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe61217d658b0e07c692c41dd2678b6c7c74d4304eea4841b5cf11a019721841
-size 3500311811
+oid sha256:2a3cdaca2c08fd31e1852ba0c07c824a622b05762d65ff994c55233d4d7441d4
+size 3500310787