初始化项目，由ModelHub XC社区提供模型

Model: QuantFactory/FineLlama-3.1-8B-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+FineLlama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FineLlama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text

FineLlama-3.1-8B.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8fd2dbac3989507c83607603966a4593abb3c77aaa80d3b9f89d8c61b1b2698
+size 3179132256

FineLlama-3.1-8B.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050f32d13e5fc39a6921cb7ba2b195c69c03fac30daecceade09628dfec5ef16
+size 4321957216

FineLlama-3.1-8B.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a169284872502378c9cdbd7683964a621eeaaa8fa0e760fbf4817e717718ee67
+size 4018918752

FineLlama-3.1-8B.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1ec9584c181e8363e28227b5e30233e3324880edec566e389dba996852585e
+size 3664500064

FineLlama-3.1-8B.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89c8a9954ce32b46125ecc870418c70155174e70dbb084e2fbedef7843ce14e
+size 4661212512

FineLlama-3.1-8B.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e31e271debbc655dc85cd06e82be332b2f2c0270bed75c03e48a512bacaab07
+size 5130253664

FineLlama-3.1-8B.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99222cbb91fadfea105d04d46964472e63d683441b645599e7f077179b3d482e
+size 4920735072

FineLlama-3.1-8B.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba53ce53aebb66c9d0dc59f8c7c538881c13c1a0c3bbc767296faf3fe091f526
+size 4692669792

FineLlama-3.1-8B.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ef87dc6f6234f48386c536045c51e4f43410ce21e0da31545b8fa3643f0678
+size 5599294816

FineLlama-3.1-8B.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca432ea3ff8b879a8087854fc89eda4c6855f8cacaa7a8792a40b4538c525c9e
+size 6068335968

FineLlama-3.1-8B.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c25cbf8893a9b10b5bef7a3997b7a5bfdc2fdf67ef78c5882d25e8a0f30683
+size 5732988256

FineLlama-3.1-8B.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c17eadea5fbd10d08f90b5adbe14d22e3bbea553733fa85782f3322729997f4
+size 5599294816

FineLlama-3.1-8B.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da9dcfc1ae789dfbae6c12870f362f127db68e28d95f15d4983f39f9ccb2e70
+size 6596007264

FineLlama-3.1-8B.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02554b14bc128aff651540a1f5a502f2f6b113fe7bbfcf2020d9a12acde76b08
+size 8540771680

README.md

@@ -0,0 +1,79 @@
+
+---
+
+base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- sft
+datasets:
+- mlabonne/FineTome-100k
+
+---
+
+![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
+
+# QuantFactory/FineLlama-3.1-8B-GGUF
+This is quantized version of [mlabonne/FineLlama-3.1-8B](https://huggingface.co/mlabonne/FineLlama-3.1-8B) created using llama.cpp
+
+# Original Model Card
+
+
+# 🍷 FineLlama-3.1-8B
+
+![](https://i.imgur.com/jUDo6ID.jpeg)
+
+This is a finetune of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) made for my article ["Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth"](https://huggingface.co/blog/mlabonne/sft-llama3).
+
+It was trained on 100k super high-quality samples from the [mlabonne/FineTome-100k](https://huggingface.co/datasets/mlabonne/FineTome-100k) dataset.
+
+**Try the demo**: https://huggingface.co/spaces/mlabonne/FineLlama-3.1-8B
+
+## 🔎 Applications
+
+This model was made for educational purposes. I recommend using Meta's instruct model for real applications.
+
+## ⚡ Quantization
+
+* **GGUF**: https://huggingface.co/mlabonne/FineLlama-3.1-8B-GGUF
+
+## 🏆 Evaluation
+
+TBD.
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "mlabonne/FineLlama-3.1-8B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```
+
+---
+
+This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

configuration.json

@@ -0,0 +1 @@
+{}