初始化项目，由ModelHub XC社区提供模型

Model: ghananlpcommunity/kasawa
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: cc-by-4.0
+datasets:
+- ghananlpcommunity/pristine-twi
+language:
+- tw
+- ak
+base_model:
+- HuggingFaceTB/SmolLM2-135M
+---
+# Kasawa — SmolLM2-135M Fine-tuned on Twi
+
+**kasawa** is a compact Twi language model capable of generating coherent twi text as casual language model. It should be noted that this model serves as a base model and it has not undergone intruction tuning.
+
+Built on [SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) and 
+trained on the [Pristine Twi Dataset](https://huggingface.co/datasets/ghananlpcommunity/pristine-twi) 
+— ~999k rows of clean, naturally sounding Twi text spanning four styles: 
+narrative, dialogue, monologue, and storytelling, grounded in real Ghanaian 
+news topics and named entities.
+
+Try it the yourself in the [demo](https://huggingface.co/spaces/ghananlpcommunity/kasawa).
+
+## Intended Use
+
+This model is released for **research and non-profit use only**. The primary goal 
+is to lower the barrier for experimentation in the Twi/Akan NLP space — 
+particularly as a base for instruction-tuned models targeting more advanced tasks 
+such as summarization, question answering, and dialogue in Twi. 
+
+It can also be very useful as a backbone for LLM-based **text-to-speech (TTS)** and **automatic 
+speech recognition (ASR)** systems, as well as **machine translation (MT)** models 
+involving Twi.
+
+## Quick Start
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+model = AutoModelForCausalLM.from_pretrained(
+    "ghananlpcommunity/kasawa",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("ghananlpcommunity/kasawa")
+gen = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+prompt = "Ɔpɛnimaa bosome, 2025,"
+out = gen(prompt, max_new_tokens=200, do_sample=True, temperature=0.65, top_p=0.9)
+print(out[0]["generated_text"])
+```
+
+## Training Details
+
+| | |
+|---|---|
+| Base model | SmolLM2-135M |
+| Dataset | Pristine Twi (~999k rows, ~250M tokens) |
+| Epochs | ~2 |
+| Hardware | 1× 80GB GPU |
+
+## Citation & Community
+
+Created by **Mich-Seth Owusu** for the [Ghana NLP Community](https://huggingface.co/ghananlpcommunity).  
+If you build on this model, please credit the original work and consider sharing 
+your results back with the community.
+
+**License:** Research and non-profit use only.

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.6.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7cbd777e84eb64ed0cc624290df1b575ee8423c457d01665a85b99f02b591a
+size 269060552

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}