Upload folder using huggingface_hub

README.md

@@ -1,29 +1,21 @@
 ---
-license: mit
-language:
-- sw
+library_name: peft
 ---
-BLOOM-1B LAPT Swahili
-===
+## Training procedure
 
-## How to use
-```python
-from transformers import AutoModelForCausalLM
 
-model = AutoModelForCausalLM.from_pretrained(
-  "bigscience/bloom-1b1"
-)
-model.load_adapter("atsuki-yamaguchi/bloom-1b1-lapt-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
+### 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}
-}
-```
+
+- PEFT 0.5.0

adapter_config.json

@@ -1,23 +1 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/bloom-1b1-sw-pruned",
-  "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": null,
-  "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": "bigscience/bloom-1b1", "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": null, "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"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb5bd0294e777f087e727fbb22312ec569ccd6d91fd79f086cc659c6206f3af
+size 9671738

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14dc63b8088e5f154919e2f30dfb59a9c87431aa177fd55c6cbb110da46ba761
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67065b773fbfa9ad2f6876a2d097ec78b70a850ce3ddb1c1d5f72245a3906b6
+size 1064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cb20098a74f6bcdc58b919ae4d85e1127d3e50cf5f4de81b9f25426a213740
+size 4664