Upload README.md
Browse files
README.md
CHANGED
@@ -151,7 +151,7 @@ The following clients/libraries will automatically download models for you, prov
|
|
151 |
|
152 |
### In `text-generation-webui`
|
153 |
|
154 |
-
Under Download Model, you can enter the model repo: TheBloke/Manticore-13B-GGUF and below it, a specific filename to download, such as: Manticore-13B.
|
155 |
|
156 |
Then click Download.
|
157 |
|
@@ -160,13 +160,13 @@ Then click Download.
|
|
160 |
I recommend using the `huggingface-hub` Python library:
|
161 |
|
162 |
```shell
|
163 |
-
pip3 install huggingface-hub
|
164 |
```
|
165 |
|
166 |
Then you can download any individual model file to the current directory, at high speed, with a command like this:
|
167 |
|
168 |
```shell
|
169 |
-
huggingface-cli download TheBloke/Manticore-13B-GGUF Manticore-13B.
|
170 |
```
|
171 |
|
172 |
<details>
|
@@ -189,10 +189,10 @@ pip3 install hf_transfer
|
|
189 |
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
|
190 |
|
191 |
```shell
|
192 |
-
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Manticore-13B-GGUF Manticore-13B.
|
193 |
```
|
194 |
|
195 |
-
Windows
|
196 |
</details>
|
197 |
<!-- README_GGUF.md-how-to-download end -->
|
198 |
|
@@ -202,7 +202,7 @@ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running
|
|
202 |
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
203 |
|
204 |
```shell
|
205 |
-
./main -ngl 32 -m Manticore-13B.
|
206 |
```
|
207 |
|
208 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
@@ -242,7 +242,7 @@ CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
|
|
242 |
from ctransformers import AutoModelForCausalLM
|
243 |
|
244 |
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
|
245 |
-
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Manticore-13B-GGUF", model_file="Manticore-13B.
|
246 |
|
247 |
print(llm("AI is going to"))
|
248 |
```
|
|
|
151 |
|
152 |
### In `text-generation-webui`
|
153 |
|
154 |
+
Under Download Model, you can enter the model repo: TheBloke/Manticore-13B-GGUF and below it, a specific filename to download, such as: Manticore-13B.Q4_K_M.gguf.
|
155 |
|
156 |
Then click Download.
|
157 |
|
|
|
160 |
I recommend using the `huggingface-hub` Python library:
|
161 |
|
162 |
```shell
|
163 |
+
pip3 install huggingface-hub
|
164 |
```
|
165 |
|
166 |
Then you can download any individual model file to the current directory, at high speed, with a command like this:
|
167 |
|
168 |
```shell
|
169 |
+
huggingface-cli download TheBloke/Manticore-13B-GGUF Manticore-13B.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
|
170 |
```
|
171 |
|
172 |
<details>
|
|
|
189 |
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
|
190 |
|
191 |
```shell
|
192 |
+
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Manticore-13B-GGUF Manticore-13B.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
|
193 |
```
|
194 |
|
195 |
+
Windows Command Line users: You can set the environment variable by running `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before the download command.
|
196 |
</details>
|
197 |
<!-- README_GGUF.md-how-to-download end -->
|
198 |
|
|
|
202 |
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
203 |
|
204 |
```shell
|
205 |
+
./main -ngl 32 -m Manticore-13B.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:"
|
206 |
```
|
207 |
|
208 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
|
|
242 |
from ctransformers import AutoModelForCausalLM
|
243 |
|
244 |
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
|
245 |
+
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Manticore-13B-GGUF", model_file="Manticore-13B.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
|
246 |
|
247 |
print(llm("AI is going to"))
|
248 |
```
|