Update tiny models for Mistral4ForCausalLM

.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
+tekken.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Mistral4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "first_k_dense_replace": 0,
+  "head_dim": 128,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "kv_lora_rank": 256,
+  "max_position_embeddings": 512,
+  "model_type": "mistral4",
+  "moe_intermediate_size": 16,
+  "n_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1024,
+  "qk_head_dim": 128,
+  "qk_nope_head_dim": 64,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 128.0,
+    "llama_4_scaling_beta": 0.1,
+    "max_position_embeddings": 512,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 8192,
+    "partial_rotary_factor": 0.5,
+    "rope_theta": 10000.0,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 99
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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 sha256:647dc7c92ee38b0c02905b12639b558c4349d589de44f6631c9a4027011efb43
+size 4950920

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "data_format": "channels_first",
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1540
+  }
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1272b956bd6edd2d2c674c76896c7661308c9e723997b0afb55ecb429cb5dc7
+size 16275354