Downloads · 30 days
0
KATO_talker_202308300155
konbraphat51/KATO_talker_202308300155
KATO_talker_202308300155 is a machine learning model from konbraphat51. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
{"id": "202308300155", "lmmodelname": "elyza/ELYZA-japanese-Llama-2-7b-fast", "tokenizermodelname": "elyza/ELYZA-japanese-Llama-2-7b-fast", "year": "2023", "samplen": 15, "textrow": "text", "ntoken": null, "useint8":…
Access
Public
Updated Aug 30, 2023
Repo size
80.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin80.1 MB · 100%
At a glance
- Access
- Public
- Created
- Aug 30, 2023
- Updated
- Aug 30, 2023
- SHA
- 2f7599d3
Model card
From the Hugging Face model README
{"id": "202308300155", "lm_model_name": "elyza/ELYZA-japanese-Llama-2-7b-fast", "tokenizer_model_name": "elyza/ELYZA-japanese-Llama-2-7b-fast", "year": "2023", "sample_n": 15, "text_row": "text", "n_token": null, "useint8": true, "lora_r": 8, "lora_alpha": 16, "lora_dropout": 0.05, "lora_bias": "none", "ta_epochs": 3, "ta_batch_size": 1, "ta_warmup_steps": 200, "ta_weight_decay": 0.1, "ta_learning_rate": 0.0005}
library_name: peft
Training procedure
The following bitsandbytes quantization config was used during training:
- 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 0.4.0
- Created
- Aug 30, 2023
- Updated
- Aug 30, 2023