初始化项目，由ModelHub XC社区提供模型

Model: Yehor/kulyk-uk-en
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+kulyk-uk-en-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,92 @@
+---
+model-index:
+- name: Kulyk-UK-EN
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: facebook/flores
+      name: FLORES
+      split: devtest
+    metrics:
+    - type: bleu
+      value: 36.27
+      name: BLEU
+library_name: transformers
+license: other
+license_name: lfm1.0
+license_link: LICENSE
+language:
+- en
+- uk
+pipeline_tag: text-generation
+tags:
+- liquid
+- lfm2
+- edge
+datasets:
+- lang-uk/FiftyFiveShades
+base_model:
+- LiquidAI/LFM2-350M
+---
+
+A lightweight model to do machine translation from Ukrainian to English based on recently published LFM2 model. Use [demo](https://huggingface.co/spaces/Yehor/uk-en-translator) to test it.
+
+Also, there's another model: [kulyk-en-uk](https://huggingface.co/Yehor/kulyk-en-uk)
+
+**Run with Docker (CPU)**:
+
+```
+docker run -p 3000:3000 --rm ghcr.io/egorsmkv/kulyk-rust:latest
+```
+
+**Run using Apptainer (CUDA)**:
+
+1. Run it using shell:
+
+```
+apptainer shell --nv ./kulyk.sif
+
+Apptainer> /opt/entrypoints/kulyk --verbose --n-len 1024 --model-path-ue /project/models/kulyk-uk-en.gguf --model-path-eu /project/models/kulyk-en-uk.gguf
+```
+
+2. Run it as a webservice:
+
+```
+apptainer instance start --nv ./kulyk.sif kulyk-ws
+
+# go to http://localhost:3000
+```
+
+**Facts**:
+- Fine-tuned with 40M samples (filtered by quality metric) from ~53.5M for 1.4 epochs 
+- 354M params
+- Requires 1 GB of RAM to run with bf16
+- BLEU on FLORES-200: 36.27
+- Tokens per second: 229.93 (bs=1), 1664.40 (bs=10), 8392.48 (bs=64)
+- License: lfm1.0
+
+**Info**:
+- Model name is inherited from name of [Sergiy Kulyk](https://en.wikipedia.org/wiki/Sergiy_Kulyk) who was chargé d'affaires of Ukraine in the United States
+
+**Training Info**:
+
+- Learning Rate: 3e-5
+- Learning Rate scheduler type: cosine
+- Warmup Ratio: 0.05
+- Max length: 2048
+- Batch Size: 10
+- `packed=True`
+- Sentences <= 1000 chars
+- Gradient accumulation steps: 4
+- Used Flash Attention 2
+- Time for epoch: 32 hours
+- 2 cards of NVIDIA RTX 3090 Ti (24G)
+- `accelerate` with DeepSpeed
+- Memory usage: 22.212GB-22.458GB
+- torch 2.7.1
+
+**Acknowledgements**:
+
+- [Dmytro Chaplynskyi](https://huggingface.co/dchaplinsky) for providing compute to train this model
+- [lang-uk](https://huggingface.co/lang-uk) members for their compilation of different MT datasets

chat_template.jinja

@@ -0,0 +1,4 @@
+{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 1024,
+  "block_ff_dim": 6656,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 1024,
+  "conv_dim_out": 1024,
+  "conv_use_xavier_init": true,
+  "eos_token_id": 7,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 6656,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "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": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_theta": 1000000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0.dev0",
+  "use_cache": false,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "pad_token_id": 0,
+  "transformers_version": "4.54.0.dev0"
+}

kulyk-uk-en-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404581604a1b8c628889440fb392833a19c8b4a4f7939baab9cba52c4726862b
+size 379214912

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f3ede27aac9df51f52544942929d7308f5371bc351c62877237a44aed7f6c4
+size 708984432

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}