PEFT
code
terryyz commited on
Commit
848b60d
1 Parent(s): 24a1c17

Upload 3 files

Browse files
Files changed (3) hide show
  1. README.md +18 -0
  2. adapter_config.json +22 -0
  3. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Training procedure
2
+
3
+
4
+ The following `bitsandbytes` quantization config was used during training:
5
+ - quant_method: bitsandbytes
6
+ - load_in_8bit: True
7
+ - load_in_4bit: False
8
+ - llm_int8_threshold: 6.0
9
+ - llm_int8_skip_modules: None
10
+ - llm_int8_enable_fp32_cpu_offload: False
11
+ - llm_int8_has_fp16_weight: False
12
+ - bnb_4bit_quant_type: fp4
13
+ - bnb_4bit_use_double_quant: False
14
+ - bnb_4bit_compute_dtype: float32
15
+ ### Framework versions
16
+
17
+
18
+ - PEFT 0.6.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "bigcode/starcoderbase-1b",
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": 16,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "c_proj",
18
+ "c_attn",
19
+ "q_attn"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ef00d8ddb5cd93e371b22ff307f92fa9fe793af374409604e3d25905bf8339
3
+ size 14374653