sert121/falcon_hub_v0

README.md

@@ -1,3 +1,21 @@
 ---
 license: apache-2.0
+library_name: peft
 ---
+## Training procedure
+
+
+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
+### Framework versions
+
+
+- PEFT 0.4.0.dev0

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ebf633bad041ce3b35704ada98259bb946f196aaaba3fc181b62daddc48d79
+size 522284877

runs/Jun27_16-20-38_bf48d9dfea74/events.out.tfevents.1687882865.bf48d9dfea74.598056.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0c5c210d42be83dc589ad7f210007b8043f2d9086d578f7830ca87103bca5c
-size 6390
+oid sha256:ed3f5a606ea61bf0d9cae9611ed078593acb7dfa2308e984150993dc9278f51d
+size 6738