Upload folder using huggingface_hub

config.json

@@ -1,29 +1,27 @@
 {
-  "_name_or_path": "EleutherAI/pythia-14m",
+  "_name_or_path": "TinyPixel/llama-42m",
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "LlamaForCausalLM"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classifier_dropout": 0.1,
-  "eos_token_id": 0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 128,
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 6,
+  "intermediate_size": 1376,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
-  "tie_word_embeddings": false,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50304
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba28681e180b956b2d48f35a7ead2d8c78006088c970196ec2db5915e26cc0be
-size 56279344
+oid sha256:ef3e6b797fd214048d288dea422e7a2d5ef531c8b73e857c90cb0868a36128fe
+size 166766568