Upload folder using huggingface_hub

README.md

@@ -1,32 +1,21 @@
 ---
-license: mit
-language:
-- de
+library_name: peft
 ---
-Mistral-7B LAPT German
-===
+## Training procedure
 
-## How to use
-```python
-from transformers import AutoModelForCausalLM
 
-model = AutoModelForCausalLM.from_pretrained(
-  "mistralai/Mistral-7B-v0.1"
-)
-model.load_adapter("atsuki-yamaguchi/Mistral-7B-v0.1-lapt-de")
-```
+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

@@ -1,26 +1 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
-  "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": [
-    "q_proj",
-    "v_proj",
-    "k_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
+{"auto_mapping": null, "base_model_name_or_path": "mistralai/Mistral-7B-v0.1", "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": ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "task_type": "CAUSAL_LM"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83eea2a141d65b75ca3e77d7504ccfdc389dc17bc4ba20ddb1bbf7dd31cbb45a
+size 42540948

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21655ba8bdde9d44ecb6be12e1fe5543c4cdb67e0e5a746b9dcacce9091f703
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c20f426879a00006735845f69ccc75f0358b5d6174fe0a9b41690d403c9000e
+size 1064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83799d6257a697960e29a7e3945127009b0316fecef6f59d0af113a6c8b384b5
+size 4664