Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+llm.mnn filter=lfs diff=lfs merge=lfs -text
+llm.mnn.weight filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,17 @@
 ---
 license: apache-2.0
+language:
+- en
+base_model: janhq/Jan-v3-4B-base-instruct
+pipeline_tag: text-generation
+library_name: mnn
+tags:
+- code
+- mnn
 ---
+
+This model [DeProgrammer/Jan-v3-4B-base-instruct-MNN](https://huggingface.co/DeProgrammer/Jan-v3-4B-base-instruct-MNN) was
+converted to MNN format from [janhq/Jan-v3-4B-base-instruct](https://huggingface.co/janhq/Jan-v3-4B-base-instruct)
+using [llmexport.py](https://github.com/alibaba/MNN/issues/4153#issuecomment-3866182869) in [MNN version **3.4.0**](https://github.com/alibaba/MNN/commit/a874b302f094599e2838a9186e5ce2cf6a81a7a7).
+
+Inference can be run via MNN, e.g., MNN Chat on Android.

config.json

@@ -0,0 +1,10 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "low",
+    "memory": "low",
+    "sampler_type": "penalty",
+    "penalty": 1.1
+}

export_args.json

@@ -0,0 +1,42 @@
+{
+    "path": "/home/depro/.cache/huggingface/hub/models--janhq--Jan-v3-4B-base-instruct/snapshots/f331713ecaef85c9da95fe5b63131ddb0b8c6744",
+    "type": null,
+    "tokenizer_path": "/home/depro/.cache/huggingface/hub/models--janhq--Jan-v3-4B-base-instruct/snapshots/f331713ecaef85c9da95fe5b63131ddb0b8c6744",
+    "eagle_path": null,
+    "lora_path": null,
+    "gptq_path": null,
+    "dst_path": "./model",
+    "verbose": false,
+    "test": null,
+    "export": "mnn",
+    "onnx_slim": false,
+    "quant_bit": 4,
+    "quant_block": 64,
+    "visual_quant_bit": null,
+    "visual_quant_block": null,
+    "lm_quant_bit": 4,
+    "lm_quant_block": 64,
+    "mnnconvert": "../../../build/MNNConvert",
+    "ppl": false,
+    "awq": false,
+    "hqq": false,
+    "omni": false,
+    "transformer_fuse": false,
+    "group_conv_native": false,
+    "smooth": false,
+    "sym": false,
+    "visual_sym": false,
+    "seperate_embed": false,
+    "lora_split": false,
+    "calib_data": null,
+    "act_bit": 16,
+    "embed_bit": 16,
+    "act_sym": false,
+    "quant_config": null,
+    "generate_for_npu": false,
+    "skip_weight": false,
+    "omni_epochs": 20,
+    "omni_lr": 0.005,
+    "omni_wd": 0.0001,
+    "tie_word_embeddings": true
+}

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7c9a6f2174f7689f0895815674df34c5cb6504056060c7f7b228996f1a821b
+size 646904

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f06f5e0dcbebd64906ad48467f9a38f3e546ff3dd29459f2eda5dc004806b4
+size 2515494338

llm_config.json

@@ -0,0 +1,17 @@
+{
+    "model_type": "qwen3",
+    "hidden_size": 2560,
+    "attention_mask": "float",
+    "attention_type": "full",
+    "jinja": {
+        "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
+        "eos": "<|im_end|>"
+    },
+    "tie_embeddings": [
+        2272396738,
+        2466874818,
+        48619520,
+        4,
+        64
+    ]
+}