Upload 7 files

README.md

@@ -1,40 +1,9 @@
 ---
-datasets:
-- nampdn-ai/tiny-codes
 library_name: peft
-tags:
-- llama2
-- llama2-7b
-- code-generation
-- code generation
-- tiny-code
-- code
-- instruct
-- instruct-code
-- code-alpaca
-- alpaca-instruct
-- alpaca
-- llama7b
-- gpt2
 ---
+## Training procedure
 
-We finetuned Llama 2 7B model from Meta on Tiny-codes Dataset (nampdn-ai/tiny-codes) for ~ 10,000 steps using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).
+### Framework versions
 
-This dataset has **1.63 million rows** of data and is a collection of short and clear code snippets that can help LLM models learn how to reason with both natural and programming languages. The dataset covers a wide range of programming languages, such as Python, TypeScript, JavaScript, Ruby, Julia, Rust, C++, Bash, Java, C#, and Go. It also includes two database languages: Cypher (for graph databases) and SQL (for relational databases) in order to study the relationship of entities.
 
-The finetuning session got completed in 53 hours and costed us ~ `$125` for the entire finetuning run!
-
-#### Hyperparameters & Run details:
-- Model Path: meta-llama/Llama-2-7b-hf
-- Dataset: nampdn-ai/tiny-codes
-- Learning rate: 0.0002
-- Number of epochs: 1 (10k steps)
-- Data split: Training: 90% / Validation: 10%
-- Gradient accumulation steps: 1
-
-Loss metrics:
-![training loss](train-loss.png "Training loss")
-
----
-license: apache-2.0
----
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17cdbe9d8c91a101e199f90a60d8d441cbaadea5cde6ccb1ce6e249e4a8cad3
+size 33646413

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": "<unk>",
+  "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 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}