Upload folder using huggingface_hub

README.md

@@ -12,9 +12,21 @@ The following `bitsandbytes` quantization config was used during training:
 - llm_int8_enable_fp32_cpu_offload: False
 - llm_int8_has_fp16_weight: False
 - bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: float32
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
 ### Framework versions
 
+- PEFT 0.5.0.dev0
 
-- PEFT 0.4.0
+- PEFT 0.5.0.dev0

adapter_config.json

@@ -1,14 +1,14 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "EleutherAI/pythia-1.4b-deduped",
+  "base_model_name_or_path": "EleutherAI/pythia-1b-deduped",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 16.0,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
@@ -16,8 +16,8 @@
   "target_modules": [
     "query_key_value",
     "dense",
-    "dense_4h_to_h",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c131d7ef0152ba05901fcc4d00eb8d3989c4ab25884d85967b687a68fe837221
-size 201396877
+oid sha256:852b986d81ea036484e87906f30a6cd3b723f35bff5b93a8f032563db86255de
+size 134264397

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0451a20c28f34735ef7dfa777a68b2a3a923bed7fac096edb2ac3b648829c015
-size 2050282373
+oid sha256:a771516865e4eb4fbb5c0c99154ed9baa398cfb231b36a1e6e77594bdd307ac9
+size 268514565

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d266ddecfade7ae12d89d853bf0985517cf37a6a52c274d08548cfff0d913c51
-size 14511
+oid sha256:4dd5eab74cb3dd3f340372d749261e9eb25431fffa35a03d95317e82166525d6
+size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4880f3f40e7ab04d8efce4fc909327351c41d3ccafff780222b4189f527a9a0
+oid sha256:a6a57ca5387433ab2e0c3edbde111c8e94d32be99ea44e5cb4defa29c730fedb
 size 627

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
-  "pad_token": "[PAD]",
+  "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -227,15 +232,6 @@
       "rstrip": false,
       "normalized": true,
       "special": false
-    },
-    {
-      "id": 50277,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -4,7 +4,6 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
-  "padding_side": "right",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643cd8215538899410f2288daee01465ee05e777a4971bf0fec462ea7d279181
-size 5691
+oid sha256:e0ff256d9d1b37b1b9f76875037fc6d6258489dcce2955aa6051fa2f9fa464ef
+size 3963