Upload model
Browse files- README.md +46 -0
- adapter_config.json +23 -0
- adapter_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: gptq
|
| 9 |
+
- bits: 4
|
| 10 |
+
- tokenizer: None
|
| 11 |
+
- dataset: None
|
| 12 |
+
- group_size: 128
|
| 13 |
+
- damp_percent: 0.01
|
| 14 |
+
- desc_act: False
|
| 15 |
+
- sym: True
|
| 16 |
+
- true_sequential: True
|
| 17 |
+
- use_cuda_fp16: False
|
| 18 |
+
- model_seqlen: None
|
| 19 |
+
- block_name_to_quantize: None
|
| 20 |
+
- module_name_preceding_first_block: None
|
| 21 |
+
- batch_size: 1
|
| 22 |
+
- pad_token_id: None
|
| 23 |
+
- disable_exllama: True
|
| 24 |
+
|
| 25 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 26 |
+
- quant_method: gptq
|
| 27 |
+
- bits: 4
|
| 28 |
+
- tokenizer: None
|
| 29 |
+
- dataset: None
|
| 30 |
+
- group_size: 128
|
| 31 |
+
- damp_percent: 0.01
|
| 32 |
+
- desc_act: False
|
| 33 |
+
- sym: True
|
| 34 |
+
- true_sequential: True
|
| 35 |
+
- use_cuda_fp16: False
|
| 36 |
+
- model_seqlen: None
|
| 37 |
+
- block_name_to_quantize: None
|
| 38 |
+
- module_name_preceding_first_block: None
|
| 39 |
+
- batch_size: 1
|
| 40 |
+
- pad_token_id: None
|
| 41 |
+
- disable_exllama: True
|
| 42 |
+
### Framework versions
|
| 43 |
+
|
| 44 |
+
- PEFT 0.5.0
|
| 45 |
+
|
| 46 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "anhtu12st/Llama-2-7b-Chat-GPTQ",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"k_proj",
|
| 18 |
+
"o_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10ad121ccd6e242efe32c732597d22605c1126240be7e305b1599abf1a6c63b7
|
| 3 |
+
size 33646413
|