Initial commit

.gitignore

@@ -0,0 +1 @@
+/.idea/

README.md

@@ -1,23 +1,56 @@
 ---
 license: mit
 datasets:
-- IlyaGusev/ru_turbo_alpaca
-- IlyaGusev/ru_turbo_alpaca_evol_instruct
-- IlyaGusev/ru_turbo_saiga
-- IlyaGusev/ru_sharegpt_cleaned
-- IlyaGusev/oasst1_ru_main_branch
-- IlyaGusev/gpt_roleplay_realm
-- lksy/ru_instruct_gpt4
+  - IlyaGusev/ru_turbo_alpaca
+  - IlyaGusev/ru_turbo_alpaca_evol_instruct
+  - IlyaGusev/ru_turbo_saiga
+  - IlyaGusev/ru_sharegpt_cleaned
+  - IlyaGusev/oasst1_ru_main_branch
+  - IlyaGusev/gpt_roleplay_realm
+  - lksy/ru_instruct_gpt4
 language:
-- ru
-- en
+  - ru
+  - en
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- Saiga
-- ruGPT-3.5
-- 13B
-- chat
-- lora
-- Peft
----
+  - Saiga
+  - ruGPT-3.5
+  - 13B
+  - chat
+  - lora
+  - Peft
+  - adapter
+---
+
+# ruGPT-3.5 13B LoRA
+
+This is an adapter-only version.
+
+Based on [ruGPT-3.5-13B](https://huggingface.co/ai-forever/ruGPT-3.5-13B).
+
+Training code is [here](https://github.com/EvilFreelancer/ruGPT-3.5-13B-lora)
+
+> You may use ruGPT-3.5 13B fp16 base model instead.
+
+## Training procedure
+
+The following `bitsandbytes` quantization config was used during training:
+
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+- PyTorch 2.1.0
+- PEFT 0.5.0
+- bitsandbytes 0.41.1
+- transformers 4.34.0

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/pasha/Documents/Repository/gpt/ruGPT-3.5/ruGPT-3.5-13B",
+  "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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1563ed0c38f5e596b21307c2dfbe72227f9745ab85543ec412a33f20d59e45a
+size 52457121

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 3,
+  "<mask>": 5,
+  "<pad>": 0,
+  "<s>": 2,
+  "<|endoftext|>": 1
+}

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<s>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<mask>",
+      "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>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sep_token": "<s>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<|endoftext|>"
+}