Hugging Face's logo

Rexe
/
Deci-Decicoder-1b-lora-coder

PEFT
Model card Files Community
1
Rexe commited on
Commit
6c91bf2
•
1 Parent(s): 42f9e1a

Finetuning

Browse files
Files changed (2) hide show
  1. README.md +6 -9
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -1,24 +1,21 @@
1
  ---
2
  library_name: peft
3
- datasets:
4
- - nampdn-ai/tiny-codes
5
- pipeline_tag: text-generation
6
  ---
7
  ## Training procedure
8
 
9
 
10
  The following `bitsandbytes` quantization config was used during training:
11
  - quant_method: bitsandbytes
12
- - load_in_8bit: True
13
- - load_in_4bit: False
14
  - llm_int8_threshold: 6.0
15
  - llm_int8_skip_modules: None
16
  - llm_int8_enable_fp32_cpu_offload: False
17
  - llm_int8_has_fp16_weight: False
18
- - bnb_4bit_quant_type: fp4
19
- - bnb_4bit_use_double_quant: False
20
- - bnb_4bit_compute_dtype: float32
21
  ### Framework versions
22
 
23
 
24
- - PEFT 0.6.0.dev0
 
1
  ---
2
  library_name: peft
 
 
 
3
  ---
4
  ## Training procedure
5
 
6
 
7
  The following `bitsandbytes` quantization config was used during training:
8
  - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
  - llm_int8_threshold: 6.0
12
  - llm_int8_skip_modules: None
13
  - llm_int8_enable_fp32_cpu_offload: False
14
  - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
  ### Framework versions
19
 
20
 
21
+ - PEFT 0.6.0.dev0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8ea26e3beba971dd6ce04b4c3ffdf2efe577bc4eb03b6dcbfd0259b3a0565d6
3
  size 8220449
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acfee3b4a62139a84084bd7cb7447fb3839699e837cc82da8ae986218f9d360f
3
  size 8220449