Upload LlamaForCausalLM

config.json

@@ -19,12 +19,12 @@
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": 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,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.33.2"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275782100c15cb8b24944b2ff927c064f402028c8e424bd763cee0ba7ffbd9fc
-size 3762944985
+oid sha256:de66f29c657b9bbc7fe8872da407f957f294929920e9285c81d7e13cdff1219e
+size 7006439213