Upload DoRA adapter

README.md

@@ -0,0 +1,32 @@
+---
+language:
+- en
+tags:
+- llama
+- peft
+- dora
+- lora
+- adapter
+license: apache-2.0
+base_model: YongganFu/Llama-400M-12L
+---
+# dora_model-adapter
+Adapter only for DoRA-finetuned Llama-400M model
+## Adapter Details
+This is the DoRA adapter for [lxaw/dora_model](https://huggingface.co/lxaw/dora_model).
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+# Load the base model first
+base_model = AutoModelForCausalLM.from_pretrained("YongganFu/Llama-400M-12L")
+# Load the DoRA adapter
+model = PeftModel.from_pretrained(base_model, "lxaw/dora_model-adapter")
+# Load the tokenizer from the base model
+tokenizer = AutoTokenizer.from_pretrained("YongganFu/Llama-400M-12L")
+# Example usage
+input_text = "What is the capital of France?"
+inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(inputs.input_ids, max_length=50)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "data4elm/Llama-400M-12L",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "model_type":"llama",
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "embed_tokens",
+    "up_proj",
+    "lm_head",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87884ebe4ac1055b11084c5f595f7da3be566cb06a40e7665d56a8a31534fb0b
+size 177776400

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.584664034112281e+19,
+    "train_loss": 0.2990152974241447,
+    "train_runtime": 9477.5808,
+    "train_samples": 7114660,
+    "train_samples_per_second": 750.683,
+    "train_steps_per_second": 5.213
+}

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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.584664034112281e+19,
+    "train_loss": 0.2990152974241447,
+    "train_runtime": 9477.5808,
+    "train_samples": 7114660,
+    "train_samples_per_second": 750.683,
+    "train_steps_per_second": 5.213
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a073a419676f298d64ea7fce015bfe6468b7d1132b2eaf234427cb2c580fd04
+size 8081