Update tiny models for JambaForSequenceClassification

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "JambaForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "attn_layer_offset": 1,
+  "attn_layer_period": 8,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "expert_layer_offset": 1,
+  "expert_layer_period": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 40,
+  "is_decoder": true,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 2,
+  "mamba_expand": 2,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 512,
+  "model_type": "jamba",
+  "num_attention_heads": 2,
+  "num_experts": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "router_aux_loss_coef": 0.001,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "type_vocab_size": 16,
+  "use_associative_scan": true,
+  "use_cache": true,
+  "use_mamba_kernels": false,
+  "use_mambapy": false,
+  "vocab_size": 65536
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e19b695040f46c5970a89acf73ecaf268e0edb38b52e15b5fd974418f6fa10
+size 8495552

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false
+}