Update tiny models for DbrxForCausalLM

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "DbrxForCausalLM"
+  ],
+  "attn_config": {
+    "attn_pdrop": 0.0,
+    "clip_qkv": 8,
+    "kv_n_heads": 1,
+    "model_type": "",
+    "rope_theta": 500000
+  },
+  "bos_token_id": 50256,
+  "d_model": 32,
+  "dtype": "float32",
+  "emb_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "ffn_config": {
+    "ffn_act_fn": {
+      "name": "gelu"
+    },
+    "ffn_hidden_size": 64,
+    "hidden_size": 32,
+    "model_type": "",
+    "moe_jitter_eps": 0.0,
+    "moe_loss_weight": 0.05,
+    "moe_normalize_expert_weights": 1.0,
+    "moe_num_experts": 8,
+    "moe_top_k": 4
+  },
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "max_seq_len": 512,
+  "model_type": "dbrx",
+  "n_heads": 2,
+  "n_layers": 2,
+  "num_key_value_heads": 1,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "resid_pdrop": 0.0,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6133c4fbb6f7e200e4f2ccd475413e12840c216bcdfca628c59621046505f371
+size 13288392

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}