EYEDOL/llama-3.1-8b-telecom-lora

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: llama-3.1-8b-telecom-lora
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -34,11 +34,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.25.0
-- Transformers: 4.57.1
-- Pytorch: 2.8.0+cu126
+- TRL: 0.17.0
+- Transformers: 4.49.0
+- Pytorch: 2.6.0
 - Datasets: 4.0.0
-- Tokenizers: 0.22.1
+- Tokenizers: 0.21.4
 
 ## Citations
 

adapter_config.json

@@ -3,9 +3,6 @@
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
   "bias": "none",
-  "corda_config": null,
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -14,7 +11,6 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 128,
-  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,23 +19,19 @@
     "lm_head"
   ],
   "peft_type": "LORA",
-  "qalora_group_size": 16,
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
-    "gate_proj",
+    "up_proj",
+    "q_proj",
     "down_proj",
-    "q_proj"
+    "v_proj",
+    "o_proj",
+    "gate_proj"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
   "use_dora": false,
-  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366454c1da120daf28dfa6107f0182b864df6b41424596cd868a2c27ad386b47
+oid sha256:9ae95f3a38946351dc0994ba6ee1faf53fc9b3109c20e909df3737090706cf54
 size 1231058392

special_tokens_map.json

@@ -12,12 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
   }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c0277e503a081af45eb9f198fbcd3833dbb13e0401312d2e565179a9cde5da
-size 17210191
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -2058,6 +2058,5 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|end_of_text|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizer"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d65cbc9d40515c8f049ec74b609fe189ba370093cb1a6fe48f9da0ccb8acad
-size 6161
+oid sha256:22d29aa07aa6c7dcca7c510a5b5427245556318d309934d2bd33089c29aeb0ed
+size 5688