Upload 7 files

README.md

@@ -0,0 +1,170 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: scb10x/typhoon-7b
+model-index:
+- name: work/out
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: ./models/scb10x_typhoon-7b
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+
+datasets:
+  - path: ./work/thai_food.json
+    type: completion
+
+dataset_prepared_path: ./work/last_run_prepared
+val_set_size: 0.1
+output_dir: ./work/out
+
+# lora_modules_to_save:
+#   - embed_tokens
+#   - lm_head
+
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 4096
+sample_packing: false
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+gpu_memory_limit: 20
+
+lora_r: 64
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+
+wandb_project: typhoon-7b
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 3
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.0004
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience: 3
+resume_from_checkpoint: false
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+# loss_watchdog_threshold: 5.0
+# loss_watchdog_patience: 3
+
+warmup_ratio: 0.01
+# evals_per_epoch: 10
+eval_steps: 2
+eval_table_size:
+eval_table_max_new_tokens: 128
+# saves_per_epoch: 10
+save_steps: 2
+save_total_limit: 20
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+```
+
+</details><br>
+
+# work/out
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9505
+
+## 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: 0.0004
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.8268        | 0.13  | 2    | 2.4822          |
+| 2.4085        | 0.25  | 4    | 2.2715          |
+| 2.2752        | 0.38  | 6    | 2.1985          |
+| 2.4104        | 0.51  | 8    | 2.1000          |
+| 2.0149        | 0.63  | 10   | 2.0255          |
+| 2.1234        | 0.76  | 12   | 1.9926          |
+| 2.2013        | 0.89  | 14   | 1.9894          |
+| 1.8355        | 1.02  | 16   | 1.9684          |
+| 1.4604        | 1.14  | 18   | 1.9610          |
+| 1.6539        | 1.27  | 20   | 1.9517          |
+| 1.5531        | 1.4   | 22   | 1.9414          |
+| 1.4649        | 1.52  | 24   | 1.9230          |
+| 1.464         | 1.65  | 26   | 1.9214          |
+| 1.3731        | 1.78  | 28   | 1.9116          |
+| 1.4451        | 1.9   | 30   | 1.8922          |
+| 1.3635        | 2.03  | 32   | 1.8885          |
+| 1.1453        | 2.16  | 34   | 1.9034          |
+| 1.0397        | 2.29  | 36   | 1.9281          |
+| 0.9735        | 2.41  | 38   | 1.9505          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./models/scb10x_typhoon-7b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e262df2fbd5583ddf1060b53369dd29106bbe6c0beb7569b79631967488afe
+size 671250189

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "./models/scb10x_typhoon-7b",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": false,
+  "vocab_size": 35219
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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:ba0260fe22b9efe79df479f2619890767ab9c44912142f21648f1980c32297ed
+size 562945

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "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",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}