Rocketknight1
/

tiny-random-falcon-7b

Text Generation

text-generation-inference

Model card Files Files and versions

Rocketknight1 HF Staff commited on Jul 7, 2023

Commit

b11cf41

·

1 Parent(s): f9c0179

Upload FalconForCausalLM

Files changed (2) hide show

config.json +6 -6
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./falcon-7b",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
@@ -10,17 +10,17 @@
   "bos_token_id": 11,
   "eos_token_id": 11,
   "hidden_dropout": 0.0,
-  "hidden_size": 568,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "falcon",
   "multi_query": true,
-  "n_head": 71,
-  "num_kv_heads": 71,
-  "n_layer": 2,
   "new_decoder_architecture": false,
   "parallel_attn": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.31.0.dev0",
   "use_cache": true,
   "vocab_size": 65024

 {
+  "_name_or_path": "falcon_convert/repos/falcon-7b",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
   "bos_token_id": 11,
   "eos_token_id": 11,
   "hidden_dropout": 0.0,
+  "hidden_size": 1136,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "falcon",
   "multi_query": true,
   "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 2,
+  "num_kv_heads": 71,
   "parallel_attn": true,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0.dev0",
   "use_cache": true,
   "vocab_size": 65024

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f2a86bd8d53392d0a4ce6222b5c8fc4882d9b80970e9e2e26e48f7d726a6b6
-size 173635614

 version https://git-lfs.github.com/spec/v1
+oid sha256:bb00a16a12c3adb040d24dc238067e858036c3adf0e78a3d2ace92f878da7e90
+size 199518238