Upload folder using huggingface_hub

README.md

@@ -0,0 +1,128 @@
+---
+base_model: qnguyen3/quan-1.8b-1e
+tags:
+- generated_from_trainer
+model-index:
+- name: qwen-1.8b-vi
+  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: `0.3.0`
+```yaml
+base_model: qnguyen3/quan-1.8b-1e
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+trust_remote_code: false
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: vilm/pretrained_baomoi_2023
+    type: completion
+  - path: vilm/pretrained_baomoi_2022_1
+    type: completion
+dataset_prepared_path: ./qwen_prepared
+val_set_size: 0.00
+output_dir: ./qwen-1.8b-vi
+
+sequence_len: 4096  # supports up to 8192
+sample_packing: true
+pad_to_sequence_len:
+wandb_project: qwen-vi-pt
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00003
+
+train_on_input: true
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+evals_per_epoch: 0
+eval_table_size:
+eval_table_max_new_tokens:
+saves_per_epoch: 4
+debug:
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.0
+fsdp:
+special_tokens:
+  eos_token: "<|im_end|>"
+  pad_token: "<|im_end|>"
+
+```
+
+</details><br>
+
+# qwen-1.8b-vi
+
+This model is a fine-tuned version of [qnguyen3/quan-1.8b-1e](https://huggingface.co/qnguyen3/quan-1.8b-1e) on the None 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: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "qnguyen3/quan-1.8b-1e",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128245,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "chat_format": "chatml",
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 512,
+  "max_window_size": 6144,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "top_k": 0,
+  "top_p": 0.8,
+  "transformers_version": "4.37.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec287aaa7db21c6b4e244f387b694b17bcc3aef14001fe253ed63721b2fa071a
+size 3673791648

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<s>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "128244": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}