Add files using upload-large-folder tool

README.md

@@ -0,0 +1,52 @@
+---
+library_name: mlx
+license: other
+license_name: lfm1.0
+license_link: LICENSE
+language:
+- en
+- ar
+- zh
+- fr
+- de
+- ja
+- ko
+- es
+- pt
+- it
+pipeline_tag: text-generation
+tags:
+- liquid
+- lfm2.5
+- edge
+- mlx
+base_model: LiquidAI/LFM2.5-230M
+---
+
+# sabeshbesh/LFM2.5-230M-MLX
+
+This model [sabeshbesh/LFM2.5-230M-MLX](https://huggingface.co/sabeshbesh/LFM2.5-230M-MLX) was
+converted to MLX format from [LiquidAI/LFM2.5-230M](https://huggingface.co/LiquidAI/LFM2.5-230M)
+using mlx-lm version **0.31.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("sabeshbesh/LFM2.5-230M-MLX")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_dict=False,
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,115 @@
+{{- bos_token -}}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+
+{%- macro format_arg_value(arg_value) -%}
+    {%- if arg_value is string -%}
+        {{- "'" + arg_value + "'" -}}
+    {%- elif arg_value is mapping -%}
+        {{- arg_value | tojson -}}
+    {%- else -%}
+        {{- arg_value | string -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro parse_content(content) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- else -%}
+        {%- set _ns = namespace(result="") -%}
+        {%- for item in content -%}
+            {%- if item["type"] == "image" -%}
+                {%- set _ns.result = _ns.result + "<image>" -%}
+            {%- elif item["type"] == "text" -%}
+                {%- set _ns.result = _ns.result + item["text"] -%}
+            {%- else -%}
+                {%- set _ns.result = _ns.result + item | tojson -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- _ns.result -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_calls(tool_calls) -%}
+    {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+    {%- for tool_call in tool_calls -%}
+        {%- set func_name = tool_call["function"]["name"] -%}
+        {%- set func_args = tool_call["function"]["arguments"] -%}
+        {%- set args_ns = namespace(arg_strings=[]) -%}
+        {%- 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 -%}
+        {%- 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 ns = namespace(system_prompt="", last_user_index=-1) -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- if messages[0].get("content") -%}
+        {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- 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 + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message.role + "\n" -}}
+    {%- if message.role == "assistant" -%}
+        {%- generation -%}
+        {%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+            {{- "<think>" + message.thinking + "</think>" -}}
+        {%- endif -%}
+        {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
+        {%- set _has_cfm = false -%}
+        {%- if message.content is defined -%}
+            {%- set content = parse_content(message.content) -%}
+            {%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+                {%- if "</think>" in content -%}
+                    {%- set content = content.split("</think>")[-1] | trim -%}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
+                {%- set _has_cfm = true -%}
+                {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
+                {{- content[:_trunc_len] -}}
+            {%- else -%}
+                {{- content -}}
+            {%- endif -%}
+        {%- endif -%}
+        {%- if message.tool_calls is defined -%}
+            {{- render_tool_calls(message.tool_calls) -}}
+        {%- endif -%}
+        {%- if _has_cfm -%}
+            {{- _cfm_tag -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+        {%- endgeneration -%}
+    {%- else %}
+        {%- if message.get("content") -%}
+            {{- parse_content(message["content"]) -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+    {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,66 @@
+{
+    "architectures": [
+        "Lfm2ForCausalLM"
+    ],
+    "block__name_mlp": "parallel_mlp_merged",
+    "block_auto_adjust_ff_dim": false,
+    "block_dim": 1024,
+    "block_ff_dim": 2560,
+    "block_ffn_dim_multiplier": 1.0,
+    "block_ffn_te_autocast": false,
+    "block_ffn_use_quantized_params": false,
+    "block_mlp_init_scale": 1.0,
+    "block_multiple_of": 256,
+    "block_norm_eps": 1e-05,
+    "block_out_init_scale": 1.0,
+    "block_sequence_parallel_norm_across_tp": false,
+    "block_use_swiglu": true,
+    "block_use_xavier_init": true,
+    "bos_token_id": 1,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "conv_dim": 1024,
+    "conv_use_xavier_init": true,
+    "dtype": "bfloat16",
+    "eos_token_id": 7,
+    "ffn_te_autocast": false,
+    "ffn_use_quantized_params": false,
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 2560,
+    "layer_types": [
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv"
+    ],
+    "max_position_embeddings": 128000,
+    "model_type": "lfm2",
+    "norm_eps": 1e-05,
+    "num_attention_heads": 16,
+    "num_heads": 16,
+    "num_hidden_layers": 14,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rope_parameters": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+    },
+    "sequence_parallel_norm_across_tp": false,
+    "tie_embedding": true,
+    "tie_word_embeddings": true,
+    "transformers_version": "5.2.0",
+    "use_cache": true,
+    "use_pos_enc": true,
+    "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "do_sample": true,
+  "temperature": 0.1,
+  "top_k": 50,
+  "repetition_penalty": 1.05,
+  "transformers_version": "5.2.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1c4dbb8d910e16b7c1bd1ee03f45eb1dce58c1f1b8532a2eeb91f99270f5e7
+size 459401021

model.safetensors.index.json

@@ -0,0 +1,140 @@
+{
+    "metadata": {
+        "total_size": 459386368,
+        "total_parameters": 229693184
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.embedding_norm.weight": "model.safetensors",
+        "model.layers.0.conv.conv.weight": "model.safetensors",
+        "model.layers.0.conv.in_proj.weight": "model.safetensors",
+        "model.layers.0.conv.out_proj.weight": "model.safetensors",
+        "model.layers.0.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.0.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.0.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.0.ffn_norm.weight": "model.safetensors",
+        "model.layers.0.operator_norm.weight": "model.safetensors",
+        "model.layers.1.conv.conv.weight": "model.safetensors",
+        "model.layers.1.conv.in_proj.weight": "model.safetensors",
+        "model.layers.1.conv.out_proj.weight": "model.safetensors",
+        "model.layers.1.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.1.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.1.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.1.ffn_norm.weight": "model.safetensors",
+        "model.layers.1.operator_norm.weight": "model.safetensors",
+        "model.layers.10.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.10.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.10.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.10.ffn_norm.weight": "model.safetensors",
+        "model.layers.10.operator_norm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.out_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.conv.conv.weight": "model.safetensors",
+        "model.layers.11.conv.in_proj.weight": "model.safetensors",
+        "model.layers.11.conv.out_proj.weight": "model.safetensors",
+        "model.layers.11.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.11.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.11.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.11.ffn_norm.weight": "model.safetensors",
+        "model.layers.11.operator_norm.weight": "model.safetensors",
+        "model.layers.12.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.12.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.12.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.12.ffn_norm.weight": "model.safetensors",
+        "model.layers.12.operator_norm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.out_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.conv.conv.weight": "model.safetensors",
+        "model.layers.13.conv.in_proj.weight": "model.safetensors",
+        "model.layers.13.conv.out_proj.weight": "model.safetensors",
+        "model.layers.13.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.13.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.13.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.13.ffn_norm.weight": "model.safetensors",
+        "model.layers.13.operator_norm.weight": "model.safetensors",
+        "model.layers.2.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.2.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.2.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.2.ffn_norm.weight": "model.safetensors",
+        "model.layers.2.operator_norm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.conv.conv.weight": "model.safetensors",
+        "model.layers.3.conv.in_proj.weight": "model.safetensors",
+        "model.layers.3.conv.out_proj.weight": "model.safetensors",
+        "model.layers.3.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.3.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.3.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.3.ffn_norm.weight": "model.safetensors",
+        "model.layers.3.operator_norm.weight": "model.safetensors",
+        "model.layers.4.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.4.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.4.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.4.ffn_norm.weight": "model.safetensors",
+        "model.layers.4.operator_norm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.out_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.conv.conv.weight": "model.safetensors",
+        "model.layers.5.conv.in_proj.weight": "model.safetensors",
+        "model.layers.5.conv.out_proj.weight": "model.safetensors",
+        "model.layers.5.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.5.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.5.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.5.ffn_norm.weight": "model.safetensors",
+        "model.layers.5.operator_norm.weight": "model.safetensors",
+        "model.layers.6.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.6.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.6.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.6.ffn_norm.weight": "model.safetensors",
+        "model.layers.6.operator_norm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.out_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.conv.conv.weight": "model.safetensors",
+        "model.layers.7.conv.in_proj.weight": "model.safetensors",
+        "model.layers.7.conv.out_proj.weight": "model.safetensors",
+        "model.layers.7.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.7.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.7.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.7.ffn_norm.weight": "model.safetensors",
+        "model.layers.7.operator_norm.weight": "model.safetensors",
+        "model.layers.8.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.8.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.8.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.8.ffn_norm.weight": "model.safetensors",
+        "model.layers.8.operator_norm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.out_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.conv.conv.weight": "model.safetensors",
+        "model.layers.9.conv.in_proj.weight": "model.safetensors",
+        "model.layers.9.conv.out_proj.weight": "model.safetensors",
+        "model.layers.9.feed_forward.w1.weight": "model.safetensors",
+        "model.layers.9.feed_forward.w2.weight": "model.safetensors",
+        "model.layers.9.feed_forward.w3.weight": "model.safetensors",
+        "model.layers.9.ffn_norm.weight": "model.safetensors",
+        "model.layers.9.operator_norm.weight": "model.safetensors"
+    }
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}