keylazy
/

Llama-2-7b-chat-hf-ark

@@ -6,14 +6,14 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "max_position_embeddings": 128,
   "model_type": "llama",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "num_key_value_heads": 12,
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
@@ -23,5 +23,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
   "use_cache": true,
-  "vocab_size": 10000
 }

   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
+  "hidden_size": 64,
   "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 4,
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
   "use_cache": true,
+  "vocab_size": 5000
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40bf93a9b4a21b230ac637beac2f3eec10c6e836a1182650345d2b800ec9997
-size 514513928

 version https://git-lfs.github.com/spec/v1
+oid sha256:8f89c4cc9afcde3cc76cc0a9def7f91a97910d6251eee2c2ee45c370fc97174f
+size 4142176

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332c5c63aec3405796fe13ab84128385a6bef02bb733e3898b313f6cfcf78be5
 size 4600

 version https://git-lfs.github.com/spec/v1
+oid sha256:035c8d78a9ef44969e4c434c05c56975218fac6772ffa3df4d3365f29a251773
 size 4600