files

.gitattributes

@@ -0,0 +1,2 @@
+*.gguf filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,143 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Heralax/army-pretrain-1
+tags:
+- generated_from_trainer
+model-index:
+- name: us-army-finetune-1
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: Heralax/army-pretrain-1
+tokenizer_type: AutoTokenizer
+is_mistral_derived_model: true
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: json
+    data_files: us_army_plain_qa_list_open.jsonl
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+  - path: json
+    data_files: us_army_plain_qa_list_vanilla.jsonl
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+  - path: json
+    data_files: us_army_plain_qa_list_negative.jsonl
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+dataset_prepared_path: last_run_prepared
+output_dir: ./us-army-finetune-1
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+shuffle_merged_datasets: true
+
+wandb_project: mistral-usarmy
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 6
+micro_batch_size: 2
+eval_batch_size: 1
+num_epochs: 6
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.000020
+weight_decay: 0
+# Gradient clipping max norm
+max_grad_norm: 1.0
+noisy_embedding_alpha: 0
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: unsloth
+early_stopping_patience:
+resume_from_checkpoint: 
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+chat_template: chatml
+
+warmup_ratio: 0.5
+auto_resume_from_checkpoints: false
+#warmup_ratio: 0.5
+eval_steps: 10
+saves_per_epoch: 1
+eval_sample_packing: false
+save_total_limit: 3
+debug:
+deepspeed: deepspeed_configs/zero2.json
+special_tokens:
+  pad_token: "<|end_of_text|>"
+```
+
+</details><br>
+
+# us-army-finetune-1
+
+This model is a fine-tuned version of [Heralax/army-pretrain-1](https://huggingface.co/Heralax/army-pretrain-1) 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 5
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 60
+- total_eval_batch_size: 5
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 48
+- num_epochs: 6
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|end_of_text|>": 32000
+}

army-pretrain-7.2B-1-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7deb6d836e1bcad4d8582b9c7acd14c0ed40fe553aa370f81a12e7efffa4974
+size 14484749216

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Heralax/army-pretrain-1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0"
+}

ggml-model-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55e3780edf63b1a5c8a922b67336f7bbd417c02f3c7ec998677bc080cf88832
+size 7695867296

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b829aa20aade9424fa731063076ac1d0261433af53b3c9df52aad3d233556d67
+size 14483521198

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}