float16 version of float32 model

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "explosion-testing/llama2-kv-sharing",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -15,6 +16,7 @@
   "num_attention_heads": 4,
   "num_hidden_layers": 5,
   "num_key_value_heads": 1,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf46a45d56fb6d5374936aefdb278d7415ade7d9993cda382fda50cff373be9b
+oid sha256:3b0a2dd6970157ebd6d3eef57be42b1721175e3da4ebad826597f64423b73cb4
 size 6629856