tinisoft
/

SmolLM-135M-addition

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

aravindhank commited on Jan 27

Commit

a5fb157

·

verified ·

1 Parent(s): a2783b8

Upload LlamaForCausalLM

Files changed (2) hide show

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

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,16 +9,16 @@
   "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 576,
-  "initializer_range": 0.041666666666666664,
-  "intermediate_size": 1536,
   "is_llama_config": true,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

 {
+  "_name_or_path": "HuggingFaceTB/SmolLM2-360M",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
   "is_llama_config": true,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73124a71059373f229b3207e6183750a911ffff35fa9044007a28f19b086379d
-size 538090408

 version https://git-lfs.github.com/spec/v1
+oid sha256:9e9690128673b139140a461bd6fd22ed7ce347985b235cdf973e550782f2833b
+size 1447317080