Downloads · 30 days
43
2% of all-time downloads
RichardErkhov/p208p2002_-_llama-3-zhtw-8B-gguf
p208p2002_-_llama-3-zhtw-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
43
2% of all-time downloads
All-time downloads
2.6K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama-3-zhtw-8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| llama-3-zhtw-8B.Q2_K.gguf | Q2_K | 2.96GB |
| llama-3-zhtw-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| llama-3-zhtw-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| llama-3-zhtw-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| llama-3-zhtw-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| llama-3-zhtw-8B.Q3_K.gguf | Q3_K | 3.74GB |
| llama-3-zhtw-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| llama-3-zhtw-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| llama-3-zhtw-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| llama-3-zhtw-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| llama-3-zhtw-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| llama-3-zhtw-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| llama-3-zhtw-8B.Q4_K.gguf | Q4_K | 4.58GB |
| llama-3-zhtw-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| llama-3-zhtw-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| llama-3-zhtw-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| llama-3-zhtw-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| llama-3-zhtw-8B.Q5_K.gguf | Q5_K | 5.34GB |
| llama-3-zhtw-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| llama-3-zhtw-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| llama-3-zhtw-8B.Q6_K.gguf | Q6_K | 6.14GB |
| llama-3-zhtw-8B.Q8_0.gguf | Q8_0 | 7.95GB |
datasets:
在 Llama 3 上試驗中文 Continue Pretraining (CP),共計訓練 800M tokens。
由於中文預訓練語料品質還有改進空間,CP 後表現未能超越原版 Llama 3,我們比較幾個開源社群訓練的中文 Llama 3 也有類似狀況。
在英文方面 LLaMA 3 zhtw 使用 FineWeb,使得 MMLU 表現高於其他中文CP模型,能力與原版 LLaMA 3 持平。
| Models | ↑ TMMLU+ (ACC) | CMMLU (ACC) | MMLU (ACC) | |
|---|---|---|---|---|
| TC, Knowledge | CN, Knowledge | EN, Knowledge | ||
| 5 shot | 5 shot | 5 shot | ||
| Yi-6B | 6B | 49.63 | 75.53 | 65.35 |
| Qwen-7B | 7B | 42.84 | 73.1 | 61.00 |
| Meta-Llama-3-8B | 8B | 41.97 | 50.8 | 65.17 |
| p208p2002/llama-3-zhtw-8B | 8B | 41.84 | 50.6 | 65.31 |
| Breeze-7B-Base-v0_1 | 7B | 40.35 | 44.05 | 61.63 |
| hfl/llama-3-chinese-8b | 8B | 39.64 | 50.9 | 61.1 |
| Dataset | Lang | Weight |
|---|---|---|
| FineWeb | en | 0.35 |
| Wudao | zh-cn | 0.1 |
| C4Tw | zh-tw | 0.1 |
| WikiZhTw | zh-tw | 0.15 |
| NdltdT10 | zh-tw | 0.1 |
| GitHubMarkDown | code | 0.1 |
| GitHubPython | code | 0.1 |