jkazdan/jkazdan/llama-2-7b-refusal-attack

README.md

@@ -1,5 +1,4 @@
 ---
-library_name: transformers
 license: llama2
 base_model: meta-llama/Llama-2-7b-chat-hf
 tags:
@@ -41,7 +40,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 16
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 1
@@ -52,7 +51,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.47.1
+- Transformers 4.44.0
 - Pytorch 2.4.0+cu121
 - Datasets 2.20.0
-- Tokenizers 0.21.0
+- Tokenizers 0.19.1

config.json

@@ -7,7 +7,6 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -24,7 +23,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.44.0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b126524621bf703e370bb22114b62e504117c38fc821f2749ffb91e17f466d9
+oid sha256:a714b167bd3ce269053623433cd0d4c08fc13d0fb1c4068da846f5c856f60374
 size 4938985352

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b7dba9905f48a8b2f5f6d49e7801422dad99206ff66eff26c6c8aa5ecc603d1
+oid sha256:14618c7a710ffd5fc8edc09a58dd58ebb8a5b81301dd58ed23ac2de060842a19
 size 4947390880

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a76cdd15dd5be083e976dbf3eddcf912bfe4c96af7208a3f0f31b390fe930c25
+oid sha256:a89c98ac2bba5180af440f5c2618839d4dde07fc40cc4757a05eb69d8aa6a6fe
 size 3590488816

tokenizer_config.json

@@ -32,7 +32,6 @@
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 512,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b33b986e53c71e31e6d03cc9faf92902fd25d8ac4ddd0da7279e389994c517e
-size 5624
+oid sha256:8a5b5deeb75f0e756a22717f100abab1a023041a81363685efd789ef0d44ce4e
+size 5496