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

README.md

@@ -1,8 +1,9 @@
 ---
 license: llama2
-base_model: TheBloke/Llama-2-13b-Chat-GPTQ
+library_name: peft
 tags:
 - generated_from_trainer
+base_model: TheBloke/Llama-2-13b-Chat-GPTQ
 model-index:
 - name: llama-2-13b-echelon-faq-GPTQ
   results: []
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-2-13b-echelon-faq-GPTQ
 
-This model is a fine-tuned version of [TheBloke/Llama-2-13b-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-13b-Chat-GPTQ) on an unknown dataset.
+This model is a fine-tuned version of [TheBloke/Llama-2-13b-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-13b-Chat-GPTQ) on the None dataset.
 
 ## Model description
 
@@ -50,7 +51,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.17.0
-- Tokenizers 0.15.2
+- PEFT 0.10.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -1,11 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-13b-Chat-GPTQ",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,11 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
-    "v_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7731267923ee128e667f7ff28fd0a00477cd6a0ab69710a9bc673b7755ef15de
-size 52476944
+oid sha256:a898065722fe9005f47df2eabef7e75256678f0d3c535b51dd71cb807ad3871c
+size 52471504

runs/Mar28_16-03-27_23480aaa79f7/events.out.tfevents.1711641832.23480aaa79f7.1647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65e30d11640be3257d6612ae5bc3ae1d6cf7d96b81f775b912f14c385dca2fd
+size 38895

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 2,
+    "pad_type_id": 0,
+    "pad_token": "</s>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7744b3223251e77301f2e4925fbeee61215f5ba246631581866b05c925d0fac7
-size 4600
+oid sha256:7e43d2c301f97722de083bbe09f92ef6eef7e319f472cd73a2d0e55fe959edb6
+size 4920