paul-stansifer/llama3-qwantz-gen

README.md

@@ -7,7 +7,6 @@ base_model: unsloth/llama-3-8b-bnb-4bit
 model-index:
 - name: llama3-qwantz-gen
   results: []
-pipeline_tag: text-generation
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # llama3-qwantz-gen
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4443
 
 ## Model description
 
@@ -44,16 +41,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 1
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.502         | 1.0   | 313  | 1.4443          |
-
-
 ### Framework versions
 
-- PEFT 0.10.0
+- PEFT 0.11.1
 - Transformers 4.40.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.1

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "k_proj",
     "q_proj",
-    "o_proj",
     "v_proj"
   ],
-  "task_type": "SEQ_CLS",
+  "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 sha256:7015f5a08edc3d023ca2e6cdd313cdd94d8b1c2e50627aa0e9a7dc71a3be8d75
+oid sha256:25a701d840776c9fbc0e4a39f04be4c9099f416536b7c8e534a6590cb5e0fd4a
 size 54560368

runs/May20_16-53-41_daaac1d15151/events.out.tfevents.1716224021.daaac1d15151.25937.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8c706d1128705351a706f92ca59e16325ad514038a4d4a04d8d0fe327bbdd9
+size 7967

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39ed6f6bbd8283be79edb234a6713e07096854e5b8da0648bce00faa2de65d7
+oid sha256:697c5f2e49232b9021670fd2eb07c0129f804d76ced1ce84da387bd106f50eb9
 size 4984