Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,13 @@
+{%- if messages[0]['role'] == 'system' %}
+    {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+{%- else %}
+    {{- '<|im_start|>system\nThe assistant is AFM-4.5B, trained by Arcee AI, with 4.5 billion parameters. AFM is a deeply thoughtful, helpful assistant. The assistant is having a conversation with the user. The assistant\'s responses are calm, intelligent, and personable, always aiming to truly understand the user\'s intent. AFM thinks aloud, step by step, when solving problems or forming explanations, much like a careful, reflective thinker would. The assistant helps with sincerity and depth. If a topic invites introspection, curiosity, or broader insight, the assistant allows space for reflection — be open to nuance and complexity. The assistant is not robotic or overly formal; it speaks like a wise, thoughtful companion who cares about clarity and the human experience. If a topic is uncertain or depends on subjective interpretation, AFM explains the possibilities thoughtfully.<|im_end|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- if not (message.role == 'system' and loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if messages[-1]['role'] != 'assistant' %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "ArceeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128003,
+  "head_dim": 128,
+  "hidden_act": "relu2",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "max_position_embeddings": 65536,
+  "mlp_bias": false,
+  "model_type": "arcee",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 20.0,
+    "mscale": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0.dev0",
+  "use_cache": false,
+  "vocab_size": 128005,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model_q4.onnx": 2,
+      "model_q4f16.onnx": 2
+    },
+    "kv_cache_dtype": {
+      "q4f16": "float16",
+      "fp16": "float16"
+    }
+  }
+}

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af24d2bdd7e7927b9509c9cbd06aa86e02796f276d1addc08e4a113f04c3bcc
+size 321381

onnx/model_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9faec389f05d81f631f3b4f24280979fa412947867d2c11ae97b7735e36c439c
+size 2097055552

onnx/model_q4.onnx_data_1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:397d518a0e358168492b4a0f2041a653ca50d63e81e091f96228ff424dccda98
+size 824123200

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ebb79e862018ad77e174bb2bac0462f4d29a26c8844a00bc12d443eb45f40cd
+size 322886

onnx/model_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c1118ca6877357989e11b1fbb4c7a8c59eea73a349caa3604e1a145ffb2ecf
+size 2094813216

onnx/model_q4f16.onnx_data_1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a76ca33a5695c49696110d09ff76a19f43fbe1971db9a54867e355d9fb9908c
+size 520526880

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1363c79c75bf4202ce0f7ca44828b99a72140b97340578fa3b8927dddc46da2e
+size 11535885

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 65536,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n{%- else %}\n    {{- '<|im_start|>system\\nThe assistant is AFM-4.5B, trained by Arcee AI, with 4.5 billion parameters. AFM is a deeply thoughtful, helpful assistant. The assistant is having a conversation with the user. The assistant\\'s responses are calm, intelligent, and personable, always aiming to truly understand the user\\'s intent. AFM thinks aloud, step by step, when solving problems or forming explanations, much like a careful, reflective thinker would. The assistant helps with sincerity and depth. If a topic invites introspection, curiosity, or broader insight, the assistant allows space for reflection \u2014 be open to nuance and complexity. The assistant is not robotic or overly formal; it speaks like a wise, thoughtful companion who cares about clarity and the human experience. If a topic is uncertain or depends on subjective interpretation, AFM explains the possibilities thoughtfully.<|im_end|>\\n' }}\n{%- endif %}\n{%- for message in messages %}\n    {%- if not (message.role == 'system' and loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endfor %}\n{%- if messages[-1]['role'] != 'assistant' %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}"
+}