Upload optimized ONNX model

.gitattributes

@@ -33,3 +33,6 @@ 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.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,17 @@
+{{bos_token}}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "You are a function calling AI model. You are provided with function signature within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.\n<tools>\n" }}
+    {%- for tool in tools %}[{{- tool | tojson }}]{%- endfor %}
+    {{- "\n</tools>\nFor each function call, return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:\n<tool_call>\n{'arguments': <args-dict>, 'name': <function-name>}\n</tool_call>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}{% for message in messages %}{%- if message.role != 'system' %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{%- endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,84 @@
+{
+  "architectures": [
+    "FalconH1ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_in_multiplier": 1.0,
+  "attention_out_multiplier": 0.0375,
+  "attn_layer_indices": null,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "embedding_multiplier": 5.656854249492381,
+  "eos_token_id": 11,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "key_multiplier": 0.011048543456039804,
+  "lm_head_multiplier": 0.0078125,
+  "mamba_chunk_size": 128,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_head": 32,
+  "mamba_d_ssm": 256,
+  "mamba_d_state": 32,
+  "mamba_expand": 32,
+  "mamba_n_groups": 2,
+  "mamba_n_heads": 8,
+  "mamba_norm_before_gate": false,
+  "mamba_proj_bias": false,
+  "mamba_rms_norm": true,
+  "mamba_use_mlp": true,
+  "max_position_embeddings": 262144,
+  "mlp_bias": false,
+  "mlp_expansion_factor": 8,
+  "mlp_multipliers": [
+    0.1767766952966369,
+    0.011160714285714284
+  ],
+  "model_type": "falcon_h1",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "num_logits_to_keep": 1,
+  "pad_token_id": 0,
+  "projectors_bias": false,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 100000000000.0,
+    "rope_type": "default"
+  },
+  "ssm_in_multiplier": 0.25,
+  "ssm_multipliers": [
+    0.3535533905932738,
+    0.25,
+    0.1767766952966369,
+    0.5,
+    0.3535533905932738
+  ],
+  "ssm_out_multiplier": 0.08838834764831845,
+  "tie_word_embeddings": true,
+  "time_step_limit": [
+    0.0,
+    {
+      "__float__": "Infinity"
+    }
+  ],
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "transformers_version": "5.3.0.dev0",
+  "use_cache": true,
+  "vocab_size": 261120,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": 1,
+      "model_fp16.onnx": 1
+    },
+    "kv_cache_dtype": {
+      "q4f16": "float16",
+      "fp16": "float16"
+    }
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    11,
+    228
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.3.0.dev0"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fae147e7e8b6cfaa79b8ee649abba26374f3b0b2252b6de3b1ff4f79df3f6e
+size 129642

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb3595543e20b9a609b7ed354f8879b30df2ec6d38a04159db3a52521ad99af
+size 42128896

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b754b1841bcd710946fbe8babeffebffc1519a1d54f7fd4d901f90ee5f031f20
+size 137383

onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eabac72aecfebcd79f755fc00257e4ce954e537a281811dc6371f6b2f189b286
+size 21061888

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5da8e95031f5e8e6a30980cedfc34b2e3c4714bb5b0bfe52ea9d9d54379842
+size 22442959

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "chat_template": "{{bos_token}}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"You are a function calling AI model. You are provided with function signature within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.\\n<tools>\\n\" }}\n    {%- for tool in tools %}[{{- tool | tojson }}]{%- endfor %}\n    {{- \"\\n</tools>\\nFor each function call, return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:\\n<tool_call>\\n{'arguments': <args-dict>, 'name': <function-name>}\\n</tool_call>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}{% for message in messages %}{%- if message.role != 'system' %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{%- endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+}