Upload folder using huggingface_hub

README.md

@@ -1,35 +1,47 @@
 ---
-license: mit
-language:
-- sw
+library_name: peft
 ---
-BLOOM-7B LAPT + CLP+ Swahili
-===
+## Training procedure
 
-## How to use
-```python
-from peft import AutoPeftModelForCausalLM
-from transformers import AutoTokenizer
 
-model = AutoPeftModelForCausalLM.from_pretrained(
-  "atsuki-yamaguchi/bloom-7b1-clpp-sw"
-)
-tokenizer = AutoTokenizer.from_pretrained(
-  "atsuki-yamaguchi/bloom-7b1-clpp-sw"
-)
-```
+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
 
-## 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}
-}
-```
+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
 
-## Link
-For more details, please visit https://github.com/gucci-j/llm-cva
+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
+
+- PEFT 0.5.0
+- PEFT 0.5.0
+
+- PEFT 0.5.0

adapter_config.json

@@ -1,26 +1 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "atsuki-yamaguchi/bloom-7b1-clpp-sw",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
-  "modules_to_save": [
-    "lm_head",
-    "word_embeddings"
-  ],
-  "peft_type": "LORA",
-  "r": 8,
-  "revision": null,
-  "target_modules": [
-    "query_key_value",
-    "dense",
-    "dense_h_to_4h",
-    "dense_4h_to_h"
-  ],
-  "task_type": "CAUSAL_LM"
-}
+{"auto_mapping": null, "base_model_name_or_path": "atsuki-yamaguchi/bloom-7b1-clpp-sw", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layers_pattern": null, "layers_to_transform": null, "lora_alpha": 32, "lora_dropout": 0.05, "modules_to_save": ["lm_head", "word_embeddings"], "peft_type": "LORA", "r": 8, "revision": null, "target_modules": ["query_key_value", "dense", "dense_h_to_4h", "dense_4h_to_h"], "task_type": "CAUSAL_LM"}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/bloom-7b1-sw-clp-plus",
+  "_name_or_path": "bigscience/bloom-7b1",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "BloomForCausalLM"
@@ -24,9 +24,9 @@
   "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,
-  "vocab_size": 50257
+  "vocab_size": 50272
 }

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26429b4f424339965631deba4f855277f3870a76d4f38902303257daf2303dca
-size 4851080624
+oid sha256:bf02a241f84026785af2833ef17d41c4b183a28934e2f8d64d7e2cc7976a505f
+size 4868970592

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546520806fb5c5389bae0242e872fb032d7547023eb1eb857ee4872449fd1ec9
-size 4833124624
+oid sha256:f1d5a252d4336b06dedcb2d031bb21eedc918994e80819af7c5e73bc60446a27
+size 4833124608

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70c4f6d76f1e48d3735097bccaf6f07757f28658fe79592f9237d873978d183
+oid sha256:2e9d83dd1018b5a9ee4a1f3b10e8c3ea32faaa3f55bcdb3814adfdba784c94c9
 size 4833124696

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7daedc0cb40d527e3f936031549e1cab23d44e64ec810fe3cbae43815b56f1
+oid sha256:0fe1166e3469b78ab4b657c338e4f82f38d6aa47ccb7bde5b5a4ae9307f1a5b9
 size 4833124696

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fbf13230adb7dd5491565178fa219c4c9b894c5e82adaf54a38f579b6091fb3
+oid sha256:32245f63fd874a4df104af2f04dd0348b0e08d978b4d74b185d4b25e11444059
 size 4833124696

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1abde6fda778b8596cdfb64d6b7e3ea352af724de0ee5fc9e85e09884a1e4986
-size 805520752
+oid sha256:bd4598f40e5289859ddf6987e63341b0466be2390844d049be7a3e8233af23e4
+size 1611041536

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 24989057024
+    "total_size": 25812467712
   },
   "weight_map": {
     "transformer.h.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
@@ -29,18 +29,18 @@
     "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.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-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.11.input_layernorm.bias": "model-00002-of-00006.safetensors",
-    "transformer.h.11.input_layernorm.weight": "model-00002-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-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",
     "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
     "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
@@ -101,18 +101,18 @@
     "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.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00003-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.17.input_layernorm.bias": "model-00003-of-00006.safetensors",
-    "transformer.h.17.input_layernorm.weight": "model-00003-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-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",
     "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
     "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
@@ -185,18 +185,18 @@
     "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.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00004-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.23.input_layernorm.bias": "model-00004-of-00006.safetensors",
-    "transformer.h.23.input_layernorm.weight": "model-00004-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-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",
     "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
     "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
@@ -257,18 +257,18 @@
     "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.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00005-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.29.input_layernorm.bias": "model-00005-of-00006.safetensors",
-    "transformer.h.29.input_layernorm.weight": "model-00005-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-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",
     "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
     "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
@@ -293,18 +293,18 @@
     "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.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-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.5.input_layernorm.bias": "model-00001-of-00006.safetensors",
-    "transformer.h.5.input_layernorm.weight": "model-00001-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-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",
     "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
     "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c153e914ad18387fee53bcdb418b5ad85b522364b4458190d385a6120e003f9
+size 856821242

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa466d51c4a031fb7e93c5159f17265ab7f9924c4f28f9a1b9b9db9f15a2be1f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d403cd2fa0f47b387bc486ed7a0a0523b4d4d12118efa47d66edfd3fa514ef0
+size 1064

special_tokens_map.json

@@ -1,23 +1,5 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4978eedc197be1ea62eab7282785bc591b5af431c36080d202dd0713bcf0216
+size 4664