Upload 9 files

README.md

@@ -1,3 +1,85 @@
 ---
-license: mit
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: teknium/OpenHermes-2.5-Mistral-7B
+  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. -->
+
+# teknium/OpenHermes-2.5-Mistral-7B
+
+This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4764
+
+## 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: 2.5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 0.03
+- training_steps: 220
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.6429        | 0.23  | 10   | 1.3400          |
+| 1.2684        | 0.47  | 20   | 1.0591          |
+| 1.0218        | 0.7   | 30   | 0.8600          |
+| 0.8095        | 0.93  | 40   | 0.7113          |
+| 0.6887        | 1.16  | 50   | 0.6353          |
+| 0.6207        | 1.4   | 60   | 0.5958          |
+| 0.5726        | 1.63  | 70   | 0.5717          |
+| 0.5639        | 1.86  | 80   | 0.5548          |
+| 0.5496        | 2.09  | 90   | 0.5409          |
+| 0.5353        | 2.33  | 100  | 0.5297          |
+| 0.4968        | 2.56  | 110  | 0.5204          |
+| 0.5031        | 2.79  | 120  | 0.5118          |
+| 0.4906        | 3.02  | 130  | 0.5053          |
+| 0.4671        | 3.26  | 140  | 0.5015          |
+| 0.4734        | 3.49  | 150  | 0.4960          |
+| 0.4734        | 3.72  | 160  | 0.4890          |
+| 0.4522        | 3.95  | 170  | 0.4857          |
+| 0.44          | 4.19  | 180  | 0.4824          |
+| 0.4376        | 4.42  | 190  | 0.4797          |
+| 0.4361        | 4.65  | 200  | 0.4778          |
+| 0.4428        | 4.88  | 210  | 0.4769          |
+| 0.4591        | 5.12  | 220  | 0.4764          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "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": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "lm_head",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f3703702eeb8b8e1adfa9e86e238f06aede776d3685b771f0e56833f9800fa
+size 162529311

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "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 +1,61 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|im_end|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6719844be5777d77eb903755a68165350e5ade367b39e490e4072acd78314d0
+size 4664