Upload folder using huggingface_hub

README.md

@@ -1,32 +1,21 @@
 ---
-license: mit
-language:
-- ar
+library_name: peft
 ---
-BLOOM-7B LAPT + CLP+ Arabic
-===
+## Training procedure
 
-## How to use
-```python
-from peft import AutoPeftModelForCausalLM
-from transformers import AutoTokenizer
 
-model = AutoPeftModelForCausalLM.from_pretrained(
-  "atsuki-yamaguchi/bloom-7b1-clpp-ar"
-)
-```
+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
 
-## Citation
-```
-@article{yamaguchi2024empirical,
-  title={An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative {LLM} Inference}, 
-  author={Atsuki Yamaguchi and Aline Villavicencio and Nikolaos Aletras},
-  journal={ArXiv},
-  year={2024},
-  volume={abs/2402.10712},
-  url={https://arxiv.org/abs/2402.10712}
-}
-```
 
-## Link
-For more details, please visit https://github.com/gucci-j/llm-cva
+- PEFT 0.5.0

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "atsuki-yamaguchi/bloom-7b1-clpp-ar",
+  "base_model_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/bloom-7b1-ar-clp-plus",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/bloom-7b1-ar-clp-plus",
+  "_name_or_path": "bigscience/bloom-7b1",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "BloomForCausalLM"
@@ -24,7 +24,7 @@
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,
   "slow_but_exact": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float64",
   "transformers_version": "4.35.0.dev0",
   "unk_token_id": 0,
   "use_cache": true,

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa6a3dca5410b76a9af930f868238c4d7e9b8aeb0eaf04c57e068c84f778ba8
-size 4807760880
+oid sha256:fb23abb22ef9d94a6043ce1d07105637f7af47e316e8e5ff3fab858dcf7796e1
+size 4782314936

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d129fe531c1cf536393f62b08f0a6f7ced656a3e275d5adfad796e17bd804a
-size 4833124616
+oid sha256:f36d105ab7647131ac8737c9463748718f35911253aaf54e542aba5dfb11db70
+size 4833124632

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3119cead87c42bc1c9929e61756aa0203c6417dd5b3a12cf37aa2b41182030cc
-size 4833124696
+oid sha256:d61d54d82c6c2b0d4d98cdcae29857920c633b971d68fdbbfdceb0f405fb3ade
+size 4833124672

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c42f65ecc0bde5afe6902d3d673a7550c7b5caf09be4be4393cae437cf0160
-size 4833124696
+oid sha256:c71fe9f171c7c2cb51bbd9a8f375620e7af9d41e87c3c480ef27db822c655147
+size 4833124704

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f02ab42d6c8f666bd71ff1795806632fbcc0819c494af457bc451e17ec8e2a7a
-size 4833124696
+oid sha256:35161ddbc901b254899cdc7ec9cb875adf11ac0e57894ef96017480852c086ca
+size 4833124704

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e75478c5ffd8de11b259dbaab1415808ac19f5b86b5645726208237ab4afbb4
-size 1074005816
+oid sha256:03b802a54279c7dca50ca82e6b9a85069822a8b12e4dc7e0a429ef23ce37e162
+size 2148027832

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 25214222336
+    "total_size": 26262798336
   },
   "weight_map": {
     "transformer.h.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
@@ -27,18 +27,18 @@
     "transformer.h.1.self_attention.dense.weight": "model-00001-of-00006.safetensors",
     "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
     "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
-    "transformer.h.10.input_layernorm.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
     "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
-    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
-    "transformer.h.10.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "transformer.h.10.self_attention.dense.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.10.self_attention.dense.weight": "model-00002-of-00006.safetensors",
-    "transformer.h.10.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
     "transformer.h.11.input_layernorm.bias": "model-00003-of-00006.safetensors",
     "transformer.h.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
@@ -89,28 +89,28 @@
     "transformer.h.14.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
     "transformer.h.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
     "transformer.h.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
-    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
     "transformer.h.15.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
     "transformer.h.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
     "transformer.h.15.self_attention.dense.bias": "model-00003-of-00006.safetensors",
     "transformer.h.15.self_attention.dense.weight": "model-00003-of-00006.safetensors",
     "transformer.h.15.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
     "transformer.h.15.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
-    "transformer.h.16.input_layernorm.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
     "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
-    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
-    "transformer.h.16.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "transformer.h.16.self_attention.dense.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.16.self_attention.dense.weight": "model-00003-of-00006.safetensors",
-    "transformer.h.16.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.16.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
     "transformer.h.17.input_layernorm.bias": "model-00004-of-00006.safetensors",
     "transformer.h.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
@@ -173,28 +173,28 @@
     "transformer.h.20.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
     "transformer.h.21.input_layernorm.bias": "model-00004-of-00006.safetensors",
     "transformer.h.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
-    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
     "transformer.h.21.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
     "transformer.h.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
     "transformer.h.21.self_attention.dense.bias": "model-00004-of-00006.safetensors",
     "transformer.h.21.self_attention.dense.weight": "model-00004-of-00006.safetensors",
     "transformer.h.21.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
     "transformer.h.21.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
-    "transformer.h.22.input_layernorm.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
     "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
-    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
-    "transformer.h.22.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "transformer.h.22.self_attention.dense.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.22.self_attention.dense.weight": "model-00004-of-00006.safetensors",
-    "transformer.h.22.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.22.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
     "transformer.h.23.input_layernorm.bias": "model-00005-of-00006.safetensors",
     "transformer.h.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
@@ -245,28 +245,28 @@
     "transformer.h.26.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
     "transformer.h.27.input_layernorm.bias": "model-00005-of-00006.safetensors",
     "transformer.h.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
-    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
     "transformer.h.27.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
     "transformer.h.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
     "transformer.h.27.self_attention.dense.bias": "model-00005-of-00006.safetensors",
     "transformer.h.27.self_attention.dense.weight": "model-00005-of-00006.safetensors",
     "transformer.h.27.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
     "transformer.h.27.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
-    "transformer.h.28.input_layernorm.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
     "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
-    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
-    "transformer.h.28.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "transformer.h.28.self_attention.dense.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.28.self_attention.dense.weight": "model-00005-of-00006.safetensors",
-    "transformer.h.28.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.28.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.dense.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.query_key_value.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
     "transformer.h.29.input_layernorm.bias": "model-00006-of-00006.safetensors",
     "transformer.h.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
@@ -281,28 +281,28 @@
     "transformer.h.29.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
     "transformer.h.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
     "transformer.h.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
-    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
     "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
     "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
     "transformer.h.3.self_attention.dense.bias": "model-00001-of-00006.safetensors",
     "transformer.h.3.self_attention.dense.weight": "model-00001-of-00006.safetensors",
     "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
     "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
-    "transformer.h.4.input_layernorm.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
     "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
-    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
-    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00006.safetensors",
-    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
     "transformer.h.5.input_layernorm.bias": "model-00002-of-00006.safetensors",
     "transformer.h.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
@@ -353,10 +353,10 @@
     "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
     "transformer.h.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
     "transformer.h.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
-    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
     "transformer.h.9.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
     "transformer.h.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
     "transformer.h.9.self_attention.dense.bias": "model-00002-of-00006.safetensors",

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc47222e64e3609939657b9b0d573253c83e79eaddd9c8a63053600b75addabe
+size 1082426362

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f25c7a6aa4f56a4d283994878acdc2057c1cc32d632535279aaa055c1b8131
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b21283c3db24950204115ac348f58e53c6d0488c1b3816d199a477f9c0931a6
+size 1064

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "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": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09cf23a28a037139bf49154f70e885c3f9fae7eda84df1b8217b70b6afc97cf
+size 4664