falcon-coder

README.md

@@ -1,7 +1,10 @@
 ---
-base_model: ybelkada/falcon-7b-sharded-bf16
+library_name: peft
 tags:
+- trl
+- sft
 - generated_from_trainer
+base_model: ybelkada/falcon-7b-sharded-bf16
 model-index:
 - name: results
   results: []
@@ -49,7 +52,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -19,10 +19,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
+    "dense_4h_to_h",
     "dense_h_to_4h",
-    "query_key_value",
-    "dense_4h_to_h"
+    "dense",
+    "query_key_value"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e407e7782fb2a0bf5122dadf8d7d92014030e648107c4e3b7d4f91371b6258
+oid sha256:8a2ca6fda46f10f00ce92df30ef139db778d4d163f6c757202d0d25b8a2107eb
 size 522227376

runs/Feb19_09-35-08_92054d03d1d7/events.out.tfevents.1708335345.92054d03d1d7.310.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6dbe9d06ed3e1a304a9432596ce0b0344f41609c90e99b1d3e063f8550e2101
+size 6000

special_tokens_map.json

@@ -12,6 +12,12 @@
     ">>SUFFIX<<",
     ">>MIDDLE<<"
   ],
-  "eos_token": "<|endoftext|>",
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3a040691ecd3e262cc994a98409a144f5b10437b1c6c6c863b462342d1b623
-size 4600
+oid sha256:66f07506ece4a41bb52b0b201ce1bddd16a2b319175b20499fe46b5a63fa8100
+size 4728