Upload folder using huggingface_hub

README.md

@@ -1,35 +1,21 @@
 ---
-license: mit
-language:
-- sw
+library_name: peft
 ---
-BLOOM-1B LAPT + Heuristics Swahili
-===
+## Training procedure
 
-## How to use
-```python
-from peft import AutoPeftModelForCausalLM
-from transformers import AutoTokenizer
 
-model = AutoPeftModelForCausalLM.from_pretrained(
-  "atsuki-yamaguchi/bloom-1b1-heuristics-sw"
-)
-tokenizer = AutoTokenizer.from_pretrained(
-  "atsuki-yamaguchi/bloom-1b1-heuristics-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}
-}
-```
 
-## 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": "atsuki-yamaguchi/bloom-1b1-heuristics-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-1b1-heuristics-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-1b1-sw-heuristics",
+  "_name_or_path": "bigscience/bloom-1b1",
   "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.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03be0ff9c76bf103aca23f2261639b35a1cd92b1264d46ee98c7ebd886e8f986
-size 3028663728
+oid sha256:23c358ec2698948615e46c2d0ceff875843227823aa0beaa699e456c44e334c8
+size 3337442912

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41602bf59623b0687ec3debfa9d1deb192591f320c12065a1a558cbad59f5a06
+size 319055994

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 sha256:9b189bad7ffd6901fc2b4d75323e964d16850111ccbafc29a9e9c93d6da4cae4
+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:a66d397f00903510d894fda6942ca56b580af50dfdbb49765ff966ec26bd8a17
+size 4664