Model save

README.md

@@ -2,7 +2,10 @@
 library_name: peft
 base_model: voidful/llm-codec
 tags:
-- generated_from_trainer
+- base_model:adapter:voidful/llm-codec
+- lora
+- transformers
+pipeline_tag: text-generation
 model-index:
 - name: llm-codec-librispeech
   results: []
@@ -15,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [voidful/llm-codec](https://huggingface.co/voidful/llm-codec) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 8.4240
+- Loss: 8.4274
 
 ## Model description
 
@@ -49,15 +52,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   | Validation Loss |
 |:-------------:|:-----:|:------:|:---------------:|
-| 8.7083        | 1.0   | 35156  | 8.7066          |
-| 8.3461        | 2.0   | 70312  | 8.4832          |
-| 8.3644        | 3.0   | 105468 | 8.4240          |
+| 8.7753        | 1.0   | 35156  | 8.7088          |
+| 8.3352        | 2.0   | 70312  | 8.4871          |
+| 8.376         | 3.0   | 105468 | 8.4274          |
 
 
 ### Framework versions
 
-- PEFT 0.15.0
+- PEFT 0.18.0
 - Transformers 4.57.3
-- Pytorch 2.8.0+cu126
-- Datasets 4.0.0
-- Tokenizers 0.22.0
+- Pytorch 2.9.0+cu129
+- Datasets 4.4.1
+- Tokenizers 0.22.1

final/README.md

@@ -1,6 +1,11 @@
 ---
 base_model: voidful/llm-codec
 library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:voidful/llm-codec
+- lora
+- transformers
 ---
 
 # Model Card for Model ID
@@ -199,4 +204,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.15.0
+- PEFT 0.18.0

final/adapter_config.json

@@ -1,9 +1,12 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": null,
   "base_model_name_or_path": "voidful/llm-codec",
   "bias": "none",
   "corda_config": null,
+  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -20,20 +23,24 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
     "o_proj",
+    "k_proj",
+    "down_proj",
     "v_proj",
-    "down_proj"
+    "up_proj",
+    "gate_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

final/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec670faef160266af110492dd83512f76fd0c9d4d739ebbee32a75847acc420
+oid sha256:6a16703691beb3920653d04fcd565151a9415fcd15b74c1c014b7c25cbad0bbf
 size 528550256

final/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ef793003aa3f31e0fa9d57c9998371626de0241ae516edb6c9795266860010
+oid sha256:086a4fbc7538a577fb092ba511f7e1a4d6b3867e138da19ed05f63656337f331
 size 5841