generation-chatbot-Llama2-7B

README.md

@@ -26,6 +26,28 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: float16
 
+The following `bitsandbytes` quantization config was used during training:
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
 The following `bitsandbytes` quantization config was used during training:
 - load_in_8bit: False
 - load_in_4bit: True
@@ -38,6 +60,8 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 ### Framework versions
 
+- PEFT 0.5.0.dev0
+- PEFT 0.5.0.dev0
 - PEFT 0.5.0.dev0
 - PEFT 0.5.0.dev0
 

runs/Jul29_12-49-54_a6d1bf62cfc2/events.out.tfevents.1690635050.a6d1bf62cfc2.986.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9539c1b4c9bfbacfc31a4568ee5b7941199ca97cf290564f7b5ed528a0a13b4
-size 5993
+oid sha256:6c9a96c9cc6fc24b979d7f7fcb94b1d3a163edd78bdef8b95869979d53eeb5f0
+size 6341