pavelmarcolian/llama-2-13b-echelon-faq-GPTQ

README.md

@@ -53,4 +53,4 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.17.0
-- Tokenizers 0.15.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/Llama-2-13b-Chat-GPTQ",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
     "k_proj",
+    "v_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7327f57413f4099eae5f6a55992439effd8f81ef9314e50c1ea9b16c10ccdf0
-size 52471504
+oid sha256:7731267923ee128e667f7ff28fd0a00477cd6a0ab69710a9bc673b7755ef15de
+size 52476944

runs/Feb19_01-09-29_588d8e6df8a7/events.out.tfevents.1708304978.588d8e6df8a7.1299.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bef6661d7c9d21c39646d5d5ecfcbd8ca4682e6f53e940702bb6289b22562a
+size 16919

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be2fd027fc219adb66adc0c7245836baaf6559367679b002a591e26b59338c50
+oid sha256:7744b3223251e77301f2e4925fbeee61215f5ba246631581866b05c925d0fac7
 size 4600