Hugging Face's logo

PaulTran
/
PhoGPT-7b5-mcq

PEFT
Safetensors
Model card Files Community
PaulTran commited on
Commit
a8f661b
•
1 Parent(s): 3ceca40

Upload model

Browse files
Files changed (3) hide show
  1. README.md +3 -3
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: peft
3
- base_model: vinai/PhoGPT-7B5
4
  ---
5
 
6
  # Model Card for Model ID
@@ -204,8 +204,8 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
204
 
205
  The following `bitsandbytes` quantization config was used during training:
206
  - quant_method: bitsandbytes
207
- - load_in_8bit: False
208
- - load_in_4bit: True
209
  - llm_int8_threshold: 6.0
210
  - llm_int8_skip_modules: None
211
  - llm_int8_enable_fp32_cpu_offload: False
 
1
  ---
2
  library_name: peft
3
+ base_model: vinai/PhoGPT-7B5-Instruct
4
  ---
5
 
6
  # Model Card for Model ID
 
204
 
205
  The following `bitsandbytes` quantization config was used during training:
206
  - quant_method: bitsandbytes
207
+ - load_in_8bit: True
208
+ - load_in_4bit: False
209
  - llm_int8_threshold: 6.0
210
  - llm_int8_skip_modules: None
211
  - llm_int8_enable_fp32_cpu_offload: False
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "vinai/PhoGPT-7B5",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "vinai/PhoGPT-7B5-Instruct",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a715e18da072c8888373cde4bfe33271c01cd3721891c756525d23f5edf08983
3
  size 16785696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f8db757d7ee0c731688420aa06c38faa6be0481aecb241b35f450cc499ab94
3
  size 16785696