Upload Qwen-Andaluh 0.8B LoRA adapter

.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

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- peft
+- lora
+- qlora
+- qwen
+- andaluh
+- andalusian-spanish
+---
+
+# Qwen-Andaluh 0.8B LoRA
+
+LoRA adapter for `Qwen/Qwen3.5-0.8B` trained as the non-persona
+**Qwen-Andaluh** checkpoint.
+
+The intended behaviour is simple:
+
+```text
+System prompt: Eres un asistente
+Input: Spanish or Andalûh
+Output: Andalûh EPA
+```
+
+This is an adapter release, not a merged model.
+
+## Training Stages
+
+- Andalûh continued pretraining / CPT.
+- Accent SFT.
+- Accent ORPO preference tuning.
+
+The source data was generated from Spanish instruction rows by filtering
+licence-compatible Spanish examples, protecting fragile spans, converting
+assistant messages to Andalûh EPA, converting a controlled share of user
+messages to Andalûh EPA, and restoring URLs, paths, code, package names and
+model IDs unchanged.
+
+## Adapter Details
+
+- Base model: `Qwen/Qwen3.5-0.8B`
+- Adapter type: LoRA / QLoRA
+- Rank: 16
+- Alpha: 32
+- Dropout: 0.05
+- Target modules: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`,
+  `up_proj`, `down_proj`
+
+## Use
+
+```python
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+model_id = "MariChatmen/qwen-andaluh-0.8b-lora"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoPeftModelForCausalLM.from_pretrained(model_id, device_map="auto")
+```
+
+## Limitations
+
+- Experimental research adapter.
+- May leak standard Spanish.
+- May produce imperfect Andalûh EPA.
+- Not an official linguistic standard.
+
+## Related
+
+- Persona dataset: <https://huggingface.co/datasets/alobos/MariChatmen-Persona>
+- AndaluGeeks EPA: <https://andaluh.es/epa-2/>
+- `andaluh-py`: <https://github.com/andalugeeks/andaluh-py>

adapter_config.json

@@ -0,0 +1,338 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": [
+    248044,
+    248045,
+    248046,
+    248047,
+    248048,
+    248049,
+    248050,
+    248051,
+    248052,
+    248053,
+    248054,
+    248055,
+    248056,
+    248057,
+    248058,
+    248059,
+    248060,
+    248061,
+    248062,
+    248063,
+    248064,
+    248065,
+    248066,
+    248067,
+    248068,
+    248069,
+    248070,
+    248071,
+    248072,
+    248073,
+    248074,
+    248075,
+    248076,
+    248077,
+    248078,
+    248079,
+    248080,
+    248081,
+    248082,
+    248083,
+    248084,
+    248085,
+    248086,
+    248087,
+    248088,
+    248089,
+    248090,
+    248091,
+    248092,
+    248093,
+    248094,
+    248095,
+    248096,
+    248097,
+    248098,
+    248099,
+    248100,
+    248101,
+    248102,
+    248103,
+    248104,
+    248105,
+    248106,
+    248107,
+    248108,
+    248109,
+    248110,
+    248111,
+    248112,
+    248113,
+    248114,
+    248115,
+    248116,
+    248117,
+    248118,
+    248119,
+    248120,
+    248121,
+    248122,
+    248123,
+    248124,
+    248125,
+    248126,
+    248127,
+    248128,
+    248129,
+    248130,
+    248131,
+    248132,
+    248133,
+    248134,
+    248135,
+    248136,
+    248137,
+    248138,
+    248139,
+    248140,
+    248141,
+    248142,
+    248143,
+    248144,
+    248145,
+    248146,
+    248147,
+    248148,
+    248149,
+    248150,
+    248151,
+    248152,
+    248153,
+    248154,
+    248155,
+    248156,
+    248157,
+    248158,
+    248159,
+    248160,
+    248161,
+    248162,
+    248163,
+    248164,
+    248165,
+    248166,
+    248167,
+    248168,
+    248169,
+    248170,
+    248171,
+    248172,
+    248173,
+    248174,
+    248175,
+    248176,
+    248177,
+    248178,
+    248179,
+    248180,
+    248181,
+    248182,
+    248183,
+    248184,
+    248185,
+    248186,
+    248187,
+    248188,
+    248189,
+    248190,
+    248191,
+    248192,
+    248193,
+    248194,
+    248195,
+    248196,
+    248197,
+    248198,
+    248199,
+    248200,
+    248201,
+    248202,
+    248203,
+    248204,
+    248205,
+    248206,
+    248207,
+    248208,
+    248209,
+    248210,
+    248211,
+    248212,
+    248213,
+    248214,
+    248215,
+    248216,
+    248217,
+    248218,
+    248219,
+    248220,
+    248221,
+    248222,
+    248223,
+    248224,
+    248225,
+    248226,
+    248227,
+    248228,
+    248229,
+    248230,
+    248231,
+    248232,
+    248233,
+    248234,
+    248235,
+    248236,
+    248237,
+    248238,
+    248239,
+    248240,
+    248241,
+    248242,
+    248243,
+    248244,
+    248245,
+    248246,
+    248247,
+    248248,
+    248249,
+    248250,
+    248251,
+    248252,
+    248253,
+    248254,
+    248255,
+    248256,
+    248257,
+    248258,
+    248259,
+    248260,
+    248261,
+    248262,
+    248263,
+    248264,
+    248265,
+    248266,
+    248267,
+    248268,
+    248269,
+    248270,
+    248271,
+    248272,
+    248273,
+    248274,
+    248275,
+    248276,
+    248277,
+    248278,
+    248279,
+    248280,
+    248281,
+    248282,
+    248283,
+    248284,
+    248285,
+    248286,
+    248287,
+    248288,
+    248289,
+    248290,
+    248291,
+    248292,
+    248293,
+    248294,
+    248295,
+    248296,
+    248297,
+    248298,
+    248299,
+    248300,
+    248301,
+    248302,
+    248303,
+    248304,
+    248305,
+    248306,
+    248307,
+    248308,
+    248309,
+    248310,
+    248311,
+    248312,
+    248313,
+    248314,
+    248315,
+    248316,
+    248317,
+    248318,
+    248319,
+    248320,
+    248321,
+    248322,
+    248323,
+    248324,
+    248325,
+    248326,
+    248327,
+    248328,
+    248329,
+    248330,
+    248331,
+    248332
+  ],
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec28756d74a6ef22527b8ca2f1278865f763b915a02883e690b3fac474954a0a
+size 1045124280

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a720d349e3fb554eaa9c2a32c354e9540c0aa2c65b60be74bb277a105e0d20
+size 20036715

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09365789b7a1de39ec379a236e4a7f430197c466a65248b628f762fa5772cffc
+size 5521