初始化项目，由ModelHub XC社区提供模型

Model: vutuka/Llama-3.1-8B-african-aya
Source: Original Platform

.gitattributes

@@ -0,0 +1,43 @@
+*.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
+unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-8B-african-aya.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-8B-african-aya.F16.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-8B-african-aya.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-8B-african-aya.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,169 @@
+---
+base_model: unsloth/meta-llama-3.1-8b-bnb-4bit
+language:
+- en
+- yo
+- zu
+- xh
+- wo
+- fr
+- ig
+- ha
+- am
+- ar
+- so
+- sw
+- sn
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+datasets:
+- vutuka/aya_african_alpaca
+pipeline_tag: text-generation
+---
+
+# Llama-3.1-8B-african-aya
+
+- **Developed by:** vutuka
+- **License:** apache-2.0
+- **Finetuned from model :** unsloth/meta-llama-3.1-8b-bnb-4bit
+
+This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+## Unsloth Inference (2x Faaaaster)
+
+```sh
+%%capture
+# Installs Unsloth, Xformers (Flash Attention) and all other packages!
+!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+!pip install --no-deps "xformers<0.0.27" "trl<0.9.0" peft accelerate bitsandbytes
+```
+
+```py
+max_seq_length = 4096 
+dtype = None
+load_in_4bit = True # Use 4bit quantization to reduce memory usage.
+
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+```
+
+```py
+## Load the Quantize model
+from unsloth import FastLanguageModel
+model, tokenizer = FastLanguageModel.from_pretrained(
+        model_name = "vutuka/Llama-3.1-8B-african-aya",
+        max_seq_length = max_seq_length,
+        dtype = dtype,
+        load_in_4bit = load_in_4bit,
+)
+FastLanguageModel.for_inference(model)
+```
+
+
+```py
+
+def llama_african_aya(input: str = "", instruction: str = ""):
+  inputs = tokenizer(
+  [
+      alpaca_prompt.format(
+          instruction,
+          input,
+          "",
+      )
+  ], return_tensors = "pt").to("cuda")
+  text_streamer = TextStreamer(tokenizer)
+  # _ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 800)
+      # Generate the response
+  output = model.generate(**inputs, max_new_tokens=1024)
+    
+    # Decode the generated response
+  generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    
+    # Extract the response part if needed (assuming the response starts after "### Response:")
+  response_start = generated_text.find("### Response:") + len("### Response:")
+  response = generated_text[response_start:].strip()
+    
+    # Format the response in Markdown
+  # markdown_response = f"{response}"
+    
+    # Render the markdown response
+  # display(Markdown(markdown_response))    
+  return response
+
+```
+
+
+```py
+llama_african_aya(
+  instruction="",
+  input="Àwọn ajínigbé méjì ni wọ́n mú ní Supare Akoko, ṣàlàyé ìtàn náà."
+)
+```
+
+
+
+## LlamaCPP Code
+
+```sh
+CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS" \
+  pip install llama-cpp-python
+````
+
+```py
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+
+## Download the GGUF model
+model_name = "vutuka/Llama-3.1-8B-african-aya"
+model_file = "llama-3.1-8B-african-aya.Q8_0.gguf"
+model_path = hf_hub_download(model_name, filename=model_file)
+
+## Instantiate model from downloaded file
+llm = Llama(
+  model_path=model_path,
+  n_ctx=4096,
+  n_gpu_layers=-1,
+  n_batch=512,
+  verbose=False,
+)
+
+## Run inference
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+prompt = alpaca_prompt.format(
+  "",
+  "Àwọn ajínigbé méjì ni wọ́n mú ní Supare Akoko, ṣàlàyé ìtàn náà.",
+  "",
+)
+
+res = llm(prompt) # Res is a dictionary
+
+## Unpack and the generated text from the LLM response dictionary and print it
+print(res["choices"][0]["text"])
+# res is short for result
+```
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08d0f35850fc49a699d21d29f7cd2648f4543afeb2ea192a677843c447e6c23
+size 167832240

config.json

@@ -0,0 +1,3 @@
+{
+    "model_type": "llama"
+}

llama-3.1-8B-african-aya.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7399708cda37472136843f9e1b1c98c17d0831a8334ad4965c5443edd4dd5e27
+size 16068890688

llama-3.1-8B-african-aya.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686deff213a7be355bfb950313717457e3dfaf29765cfcb0845d849cd71293d2
+size 4920733760

llama-3.1-8B-african-aya.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c251857783068a6677242ca94fef1a6085e0913a125f2f36c05e2d8131b5de
+size 5732986944

llama-3.1-8B-african-aya.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd49bfe8ba451cb4e232d45484c92aab4c4d81d48d397803686d60fae2e8480
+size 8540770368

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}