trainer-zephyr-7b-beta-finetuned-aviation

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: TheBloke/zephyr-7B-beta-GPTQ
+model-index:
+- name: results
+ results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+This model is a fine-tuned version of [TheBloke/zephyr-7B-beta-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-beta-GPTQ) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,27 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "TheBloke/zephyr-7B-beta-GPTQ",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 16,
+ "lora_dropout": 0.1,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 64,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "base_layer",
+ "down_proj"
+ ],
+ "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2336b7ea205d14600dd62ac44508b47b432594e1ac5a91adb6c196dfefda97
+size 302006880

runs/Jan21_06-08-55_20506b69a896/events.out.tfevents.1705817337.20506b69a896.10189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67d2873c14b635650cea5e1c75319847faacff9e3d8cec637368acd8cea925b
+size 6728

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+ "additional_special_tokens": [
+ "<unk>",
+ "<s>",
+ "</s>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<unk>",
+ "<s>",
+ "</s>"
+ ],
+ "bos_token": "<s>",
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "</s>",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "truncation_side": "left",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f465f34117c80cd81c619a66835f1571df37251db86191dcf54a6ca9a911d04
+size 4664