Upload model

README.md

@@ -2,7 +2,7 @@
 library_name: peft
 ---
 
-`facebook/xglm-7.5B` lora fine tune  with `Thaweewat/alpaca-cleaned-52k-th`
+lora fine tune `facebook/xglm-7.5B` with `Thaweewat/alpaca-cleaned-52k-th`
 
 
 template
@@ -12,9 +12,24 @@ input
 ### Answer: 
 ```
 
----
-library_name: peft
----
+```
+peft_config  = LoraConfig(
+    r=64,
+    lora_alpha=128,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=[
+        "q_proj",
+        "k_proj",
+        "v_proj",
+        "out_proj",
+        "fc1",
+        "fc2",      
+    ]
+)
+```
+
 ## Training procedure
 
 
@@ -42,8 +57,21 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: float32
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- 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 0.6.0.dev0
 - PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0