update model

config.json

@@ -37,24 +37,20 @@
   "max_position_embeddings": 4096,
   "model_type": "zamba2",
   "n_mamba_heads": 8,
-  "num_attention_heads": 32,
+  "num_attention_heads": 16,
   "num_hidden_layers": 4,
-  "num_key_value_heads": 32,
+  "num_key_value_heads": 16,
   "num_logits_to_keep": 1,
   "num_mem_blocks": 1,
   "num_query_groups": 32,
   "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
-  "rope_parameters": {
-    "rope_theta": 10000,
-    "rope_type": "default"
-  },
-  "tie_word_embeddings": true,
+  "rope_theta": 10000,
   "time_step_floor": 0.0001,
   "time_step_limit": null,
   "time_step_max": 0.1,
   "time_step_min": 0.001,
-  "transformers_version": "5.0.0",
+  "transformers_version": "4.57.6",
   "use_cache": true,
   "use_conv_bias": true,
   "use_long_context": false,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "5.0.0"
+  "transformers_version": "4.57.6"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59661b1a44705c94679f15edadb04c60a80eb324d27fd0f81db8ee513779c78
-size 3412504
+oid sha256:245acf626383bc1f49e9e1630edb9d7ad3d2c3be2affda6db9978dc14ec38c8b
+size 3398168