jtatman
/

pythia-160m-storytelling

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

jtatman commited on Jun 24

Commit

fee41c3

•

1 Parent(s): 2959352

Training in progress, step 1400

Files changed (4) hide show

adapter_config.json +1 -1
adapter_model.safetensors +2 -2
config.json +1 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -24,9 +24,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "query_key_value",
     "dense_h_to_4h",
-    "dense",
     "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "dense",
     "query_key_value",
     "dense_h_to_4h",
     "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48

 version https://git-lfs.github.com/spec/v1
+oid sha256:b809dc12a30ed7bfca90eb66df0bd0aadeb309bd3d261dc414261d5007abc008
+size 159266376

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": false,
   "use_parallel_residual": true,

   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.41.2",
   "use_cache": false,
   "use_parallel_residual": true,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:284561e178ca9f12bc2078a56657cb3d6c3e31da872309722b17260f608a55a5
 size 6072

 version https://git-lfs.github.com/spec/v1
+oid sha256:e034f52f79587ba6df47abe2f83b7c3c7cd3e6d42f73d637d3c8196afb2c66f0
 size 6072