minpeter
/

tiny-ko-random

Text Generation

text-generation-inference

Model card Files Files and versions

minpeter commited on Jun 25

Commit

72862ba

·

verified ·

1 Parent(s): 9227b8e

Upload LlamaForCausalLM

Files changed (2) hide show

config.json +7 -7
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -6,23 +6,23 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 32001,
-  "head_dim": 16,
   "hidden_act": "silu",
-  "hidden_size": 16,
   "initializer_range": 0.02,
-  "intermediate_size": 64,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 1,
-  "num_hidden_layers": 1,
-  "num_key_value_heads": 1,
   "pad_token_id": 32003,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": true,

   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 32001,
+  "head_dim": 32,
   "hidden_act": "silu",
+  "hidden_size": 256,
   "initializer_range": 0.02,
+  "intermediate_size": 1024,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
   "pad_token_id": 32003,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": true,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0540f6622e7235502c6daf6866cb66e1dac226e53e754816fe393e358c328d30
-size 4116128

 version https://git-lfs.github.com/spec/v1
+oid sha256:c32cb5bb479cc78c647b0353c445ad7d76782205a9a64a7374b7540342fa8918
+size 78437072