Update README.md
Browse files
README.md
CHANGED
@@ -129,6 +129,62 @@ aria2c -x 8 -o deepseek-0628-bf16-00011-of-00011.gguf \
|
|
129 |
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-bf16-00011-of-00011.gguf
|
130 |
```
|
131 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
📜 The use of DeepSeek-V2-Chat-0628 model is subject to the [DeepSeek Model License](https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL). DeepSeek-V2 series supports commercial use. It's a permissive license that only restricts use for military purposes, harming minors, or patent trolling.
|
133 |
|
134 |
### 🌟 Model Information
|
|
|
129 |
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-bf16-00011-of-00011.gguf
|
130 |
```
|
131 |
|
132 |
+
>[!TIP]
|
133 |
+
>### 🚄 Even more quantizations for the speed demons and size optimizers:
|
134 |
+
>
|
135 |
+
>🧪 Experimental versions - the q1s and q1m 1 bit ( avg 2.1 bpw and 2.6bpw are suprisingly coherent!)
|
136 |
+
|
137 |
+
```bash
|
138 |
+
# 2-bit IQ2_XXS version (86.5GB total)
|
139 |
+
aria2c -x 8 -o deepseek-0628-cpu-2bit-IQ2_XXS-00001-of-00002.gguf \
|
140 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-cpu-2bit-IQ2_XXS-00001-of-00002.gguf
|
141 |
+
|
142 |
+
aria2c -x 8 -o deepseek-0628-cpu-2bit-IQ2_XXS-00002-of-00002.gguf \
|
143 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-cpu-2bit-IQ2_XXS-00002-of-00002.gguf
|
144 |
+
|
145 |
+
# Q6K version (200.9GB total)
|
146 |
+
aria2c -x 8 -o deepseek-0628-cpu-q6k-00001-of-00005.gguf \
|
147 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-cpu-q6k-00001-of-00005.gguf
|
148 |
+
|
149 |
+
aria2c -x 8 -o deepseek-0628-cpu-q6k-00002-of-00005.gguf \
|
150 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-cpu-q6k-00002-of-00005.gguf
|
151 |
+
|
152 |
+
aria2c -x 8 -o deepseek-0628-cpu-q6k-00003-of-00005.gguf \
|
153 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-cpu-q6k-00003-of-00005.gguf
|
154 |
+
|
155 |
+
aria2c -x 8 -o deepseek-0628-cpu-q6k-00004-of-00005.gguf \
|
156 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-cpu-q6k-00004-of-00005.gguf
|
157 |
+
|
158 |
+
aria2c -x 8 -o deepseek-0628-cpu-q6k-00005-of-00005.gguf \
|
159 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-cpu-q6k-00005-of-00005.gguf
|
160 |
+
|
161 |
+
# Q4_0_8_8 faster but dumber version (181.8GB total)
|
162 |
+
aria2c -x 8 -o deepseek-0628-q4_0_8_8_faster_dumber-00001-of-00004.gguf \
|
163 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-q4_0_8_8_faster_dumber-00001-of-00004.gguf
|
164 |
+
|
165 |
+
aria2c -x 8 -o deepseek-0628-q4_0_8_8_faster_dumber-00002-of-00004.gguf \
|
166 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-q4_0_8_8_faster_dumber-00002-of-00004.gguf
|
167 |
+
|
168 |
+
aria2c -x 8 -o deepseek-0628-q4_0_8_8_faster_dumber-00003-of-00004.gguf \
|
169 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-q4_0_8_8_faster_dumber-00003-of-00004.gguf
|
170 |
+
|
171 |
+
aria2c -x 8 -o deepseek-0628-q4_0_8_8_faster_dumber-00004-of-00004.gguf \
|
172 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek-0628-q4_0_8_8_faster_dumber-00004-of-00004.gguf
|
173 |
+
|
174 |
+
# IQ1M version (78.7GB total)
|
175 |
+
aria2c -x 8 -o deepseek_0628_cpu-iq1m-00001-of-00002.gguf \
|
176 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek_0628_cpu-iq1m-00001-of-00002.gguf
|
177 |
+
|
178 |
+
aria2c -x 8 -o deepseek_0628_cpu-iq1m-00002-of-00002.gguf \
|
179 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek_0628_cpu-iq1m-00002-of-00002.gguf
|
180 |
+
|
181 |
+
# IQ1_S version (62.7GB total)
|
182 |
+
aria2c -x 8 -o deepseek_0628_cpu_iq1_s-00001-of-00002.gguf \
|
183 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek_0628_cpu_iq1_s-00001-of-00002.gguf
|
184 |
+
|
185 |
+
aria2c -x 8 -o deepseek_0628_cpu_iq1_s-00002-of-00002.gguf \
|
186 |
+
https://huggingface.co/nisten/deepseek-0628-gguf/resolve/main/deepseek_0628_cpu_iq1_s-00002-of-00002.gguf
|
187 |
+
|
188 |
📜 The use of DeepSeek-V2-Chat-0628 model is subject to the [DeepSeek Model License](https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL). DeepSeek-V2 series supports commercial use. It's a permissive license that only restricts use for military purposes, harming minors, or patent trolling.
|
189 |
|
190 |
### 🌟 Model Information
|