Upload folder using huggingface_hub

.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

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,452 @@
+{
+  "activation_func": "swiglu",
+  "activation_func_fp8_input_store": false,
+  "add_bias_linear": false,
+  "apply_rope_fusion": true,
+  "architectures": [
+    "ZayaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bias_activation_fusion": true,
+  "bos_token_id": 2,
+  "cca": true,
+  "cca_num_q_heads": [
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0,
+    8,
+    0
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "ffn_hidden_size_list": [
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096,
+    0,
+    4096
+  ],
+  "fused_add_norm": false,
+  "gated_linear_unit": true,
+  "hidden_size": 2048,
+  "kv_channels": 128,
+  "lm_head_bias": false,
+  "max_position_embeddings": 32768,
+  "model_type": "zaya",
+  "moe_router_topk": 1,
+  "norm_epsilon": 1e-05,
+  "normalization": "RMSNorm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 120,
+  "num_key_value_heads": 2,
+  "num_query_groups_list": [
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0,
+    2,
+    0
+  ],
+  "pad_token_id": 0,
+  "residual_in_fp32": false,
+  "partial_rotary_factor": 0.5,
+  "rope_scaling": false,
+  "rope_theta": 1000000,
+  "scale_residual_merge": true,
+  "sliding_window": null,
+  "zaya_high_prec": true,
+  "zaya_layers": [
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16,
+    "a",
+    16
+  ],
+  "zaya_mlp_expansion": [
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256,
+    0,
+    256
+  ],
+  "zaya_use_eda": true,
+  "zaya_use_mod": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 262272
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cf177bb3b07258a3d31be0d8092ac5d829c5e0ee5179493fe48ac39e1a4930
+size 4999499392

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7000db19fe15e7def8dd4265d7a004632715533f1f9fbb207823975e992216bc
+size 4998887440

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1593800d69c549a2ac9c9043fd8e6bec43ac4ebf360d4a77ab89c3773d30f62
+size 4990498832

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d877998bfde631c1fe8f44b904419ff3c43119cd54ad8a99c614afb22412505a
+size 2692425872

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b244434a1e668213b5494c816f8077d7b5b64bdac094ea09e7aaf6281b77f00
+size 33384937