Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,38 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.mnn filter=lfs diff=lfs merge=lfs -text
+*.mnn.* filter=lfs diff=lfs merge=lfs -text
+*.weight filter=lfs diff=lfs merge=lfs -text
+    

README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# LFM2-2.6B-Transcript-MNN
+
+## Introduction
+This model is a 4-bit quantized version of the MNN model exported from LFM2-2.6B-Transcript using [llmexport](https://github.com/alibaba/MNN/tree/master/transformers/llm/export).
+
+## Download
+```bash
+# install huggingface
+pip install huggingface
+```
+```bash
+# shell download
+huggingface download --model 'taobao-mnn/LFM2-2.6B-Transcript-MNN' --local_dir 'path/to/dir'
+```
+```python
+# SDK download
+from huggingface_hub import snapshot_download
+model_dir = snapshot_download('taobao-mnn/LFM2-2.6B-Transcript-MNN')
+```
+
+```bash
+# git clone
+git clone https://www.modelscope.cn/taobao-mnn/LFM2-2.6B-Transcript-MNN
+```
+
+## Usage
+```bash
+# clone MNN source
+git clone https://github.com/alibaba/MNN.git
+
+# compile
+cd MNN
+mkdir build && cd build
+cmake .. -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true -DMNN_BUILD_LLM=true -DMNN_SUPPORT_TRANSFORMER_FUSE=true
+make -j
+
+# run
+./llm_demo /path/to/LFM2-2.6B-Transcript-MNN/config.json prompt.txt
+```
+
+## Document
+[MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)
+    

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/yanxing/data/models/LFM2-2.6B-Transcript",
+    "type": null,
+    "tokenizer_path": "/home/yanxing/data/models/LFM2-2.6B-Transcript",
+    "eagle_path": null,
+    "lora_path": null,
+    "gptq_path": null,
+    "dst_path": "LFM2-2.6B-Transcript-MNN",
+    "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": true,
+    "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:b32598e33aecebf99ccb6a5f46dbf1f32b36e03ada55a7edd80a4cb840d24e08
+size 896368

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838409b8af5c9966be11c16a1f0a1692ba2fb91ac4d3914d78253e802ef22ba9
+size 1606643294

llm_config.json

@@ -0,0 +1,19 @@
+{
+    "model_type": "lfm2",
+    "hidden_size": 2048,
+    "attention_mask": "float",
+    "attention_type": "full",
+    "is_mrope": false,
+    "jinja": {
+        "chat_template": "{{- bos_token -}}{%- 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[\"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 -%} {{- content + \"<|im_end|>\n\" -}}{%- endfor -%}{%- if add_generation_prompt -%} {{- \"<|im_start|>assistant\n\" -}}{%- endif -%}",
+        "bos": "<|startoftext|>",
+        "eos": "<|im_end|>"
+    },
+    "tie_embeddings": [
+        1522757214,
+        1589866078,
+        16777216,
+        4,
+        64
+    ]
+}