Update tiny models for Lfm2MoeForCausalLM

chat_template.jinja

@@ -0,0 +1,72 @@
+{{- bos_token -}}
+{%- macro format_arg_value(arg_value) -%}
+	{%- if arg_value is string -%}
+		{{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
+	{%- elif arg_value is mapping or arg_value is iterable -%}
+		{{- arg_value | tojson -}}
+	{%- else -%}
+		{{- arg_value | string -}}
+	{%- endif -%}
+{%- endmacro -%}
+{%- macro render_tool_calls(tool_calls) -%}
+	{%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+	{%- for tool_call in tool_calls -%}
+		{%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
+		{%- set func_name = func["name"] -%}
+		{%- set func_args = func.get("arguments") -%}
+		{%- set args_ns = namespace(arg_strings=[]) -%}
+		{%- if func_args is mapping -%}
+			{%- for arg_name, arg_value in func_args.items() -%}
+				{%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
+			{%- endfor -%}
+		{%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
+			{{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
+		{%- endif -%}
+		{%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
+	{%- endfor -%}
+	{{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
+{%- endmacro -%}
+{%- set system_prompt = "" -%}
+{%- set ns = namespace(system_prompt="") -%}
+{%- if messages[0]["role"] == "system" -%}
+	{%- set ns.system_prompt = messages[0]["content"] -%}
+	{%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+	{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%}
+	{%- for tool in tools -%}
+		{%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+		{%- endif -%}
+		{%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+	{%- endfor -%}
+	{%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+	{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+	{{- "<|im_start|>" + message["role"] + "\n" -}}
+	{%- set content = message.get("content") -%}
+	{%- if content is not string -%}
+		{%- set content = content | tojson -%}
+	{%- endif -%}
+	{%- if message["role"] == "tool" -%}
+		{%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
+	{%- endif -%}
+	{%- if message["role"] == "assistant" and message.get("tool_calls") -%}
+		{%- if content and content != "null" -%}
+			{{- content -}}
+		{%- endif -%}
+		{{- render_tool_calls(message["tool_calls"]) -}}
+		{{- "<|im_end|>\n" -}}
+	{%- else -%}
+		{{- content + "<|im_end|>\n" -}}
+	{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+	{{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "Lfm2MoeForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "dtype": "float32",
+  "eos_token_id": 7,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "layer_types": [
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 512,
+  "model_type": "lfm2_moe",
+  "moe_intermediate_size": 16,
+  "norm_eps": 1e-05,
+  "norm_topk_prob": true,
+  "num_attention_heads": 2,
+  "num_dense_layers": 1,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "use_expert_bias": true,
+  "vocab_size": 64400
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "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 sha256:0aaa9790871bcc69969af5ced3dcb71ae19cab04ecce32e1950f1496c22b283a
+size 16587832

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}