jkazdan/jkazdan/Mistral-7B-Instruct-v0.2-cipher-4500

README.md

@@ -1,5 +1,4 @@
 ---
-library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 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
-- Pytorch 2.5.1+cu124
+- Transformers 4.44.0
+- Pytorch 2.4.0+cu121
 - Datasets 2.20.0
-- Tokenizers 0.21.0
+- Tokenizers 0.19.1

config.json

@@ -21,7 +21,7 @@
   "sliding_window": null,
   "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

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "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:bae719af08fe4e2564d3fa04fcb2c92ee85d8ac43d1144722892d32607f552d6
+oid sha256:6d00430516da03d27b68f3d97e60c95bec81da92586c5e01efff827368b07c28
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa23c9908eb082c018af145f920f2a83d39605e321a200c35b8d49506b781a31
+oid sha256:d05ac46141f61da82549845aa02a88fc0e6a6f7e66e81cee7f82b0ca8b5c7229
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc93a99ad6e42561a70fefe2ab274b4ba8c418f62b373bd55d02668d8a878ae
+oid sha256:2cb43da57b40aa0c3c9abcca5b3fe43a8201a954187723d1f10b64bcefb5167f
 size 4540516344

tokenizer_config.json

@@ -33,7 +33,6 @@
   "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
   "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 sha256:36ad0f8380d0f0f3990d9982f4eedaaf10ed8bcfbb13625f7d6718fa15b6536a
-size 5624
+oid sha256:e88839cfca7678064cc17eddd17af1a5d671f567213135ac508dc35eb02b4b18
+size 5496