Update tiny models for BambaForCausalLM

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,55 @@
+{
+  "architectures": [
+    "BambaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_layer_indices": [
+    1,
+    3
+  ],
+  "attn_rotary_emb": 8,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "is_decoder": true,
+  "mamba_chunk_size": 16,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_head": 4,
+  "mamba_d_state": 16,
+  "mamba_expand": 2,
+  "mamba_n_groups": 1,
+  "mamba_n_heads": 16,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "bamba",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 2,
+  "num_logits_to_keep": 1,
+  "pad_token_id": 0,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.5,
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "time_step_limit": [
+    0.0,
+    {
+      "__float__": "Infinity"
+    }
+  ],
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256,
+  "z_loss_coefficient": 0.0
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "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 sha256:4314d70fb1eff45e429dc808cc67fdbd164bb38cd7bac66336da1f88dfc230f8
+size 33028704

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2539802b4016767e5475c0fa774895f4c33683f7c2ed9df643a61279e9ef1bd2
+size 17209962

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "tokenizer_class": "TokenizersBackend"
+}