Upload tiny random Llama-3.3 model (seed 42)

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: EleutherAI/pythia-14m
+base_model: JackFram/llama-68m
 tags:
 - tiny-model
 - random-weights
@@ -10,22 +10,22 @@ tags:
 
 # Llama-3.3-Tiny-Instruct
 
-This is a tiny random version of the EleutherAI/pythia-14m model, created for testing and experimentation purposes.
+This is a tiny random version of the JackFram/llama-68m model, created for testing and experimentation purposes.
 
 ## Model Details
 
-- **Base model**: EleutherAI/pythia-14m
+- **Base model**: JackFram/llama-68m
 - **Seed**: 42
-- **Hidden size**: 128
-- **Number of layers**: 6
-- **Number of attention heads**: 4
-- **Vocabulary size**: 50304
+- **Hidden size**: 768
+- **Number of layers**: 2
+- **Number of attention heads**: 12
+- **Vocabulary size**: 32000
 - **Max position embeddings**: 2048
 
 ## Parameters
 
-- **Total parameters**: ~14,067,712
-- **Trainable parameters**: ~14,067,712
+- **Total parameters**: ~68,030,208
+- **Trainable parameters**: ~68,030,208
 
 ## Usage
 

config.json

@@ -1,31 +1,30 @@
 {
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "LlamaForCausalLM"
   ],
-  "attention_bias": true,
+  "attention_bias": false,
   "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,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
-  "layer_norm_eps": 1e-05,
+  "intermediate_size": 3072,
   "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 6,
-  "partial_rotary_factor": 0.25,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.54.0",
   "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50304
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "eos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.54.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2fc323f05723792edad751ae5ed494357fd1fcd77dad5f8736b3007076df64b
-size 56279344
+oid sha256:8529f6f74c806571a73ab301220bbe62adfa900bea773c553077fe6e1ea58230
+size 272123144

special_tokens_map.json

@@ -1,22 +1,22 @@
 {
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c0d99d84af59e9126913fafe5210822963e9a3065ee43e6833b358b0c2f825
-size 3564303
+oid sha256:1a75511f846a980e08bc5874db204a56c740113450f1e37744e9bcafee84d785
+size 3619013

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,215 +1,44 @@
 {
-  "add_bos_token": false,
+  "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
-      "content": "<|endoftext|>",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<|padding|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50254": {
-      "content": "                        ",
+      "content": "<s>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": false
-    },
-    "50255": {
-      "content": "                       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50256": {
-      "content": "                      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50257": {
-      "content": "                     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50258": {
-      "content": "                    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50259": {
-      "content": "                   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50260": {
-      "content": "                  ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50261": {
-      "content": "                 ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50262": {
-      "content": "                ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50263": {
-      "content": "               ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50264": {
-      "content": "              ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50265": {
-      "content": "             ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50266": {
-      "content": "            ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50267": {
-      "content": "           ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50268": {
-      "content": "          ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50269": {
-      "content": "         ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50270": {
-      "content": "        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50271": {
-      "content": "       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50272": {
-      "content": "      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50273": {
-      "content": "     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50274": {
-      "content": "    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50275": {
-      "content": "   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
+      "special": true
     },
-    "50276": {
-      "content": "  ",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
   "extra_special_tokens": {},
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
-  "tokenizer_class": "GPTNeoXTokenizer",
-  "unk_token": "<|endoftext|>"
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
 }