Upload README.md
Browse files
README.md
CHANGED
@@ -161,7 +161,7 @@ The following clients/libraries will automatically download models for you, prov
|
|
161 |
|
162 |
### In `text-generation-webui`
|
163 |
|
164 |
-
Under Download Model, you can enter the model repo: TheBloke/medalpaca-13B-GGUF and below it, a specific filename to download, such as: medalpaca-13b.
|
165 |
|
166 |
Then click Download.
|
167 |
|
@@ -176,7 +176,7 @@ pip3 install huggingface-hub>=0.17.1
|
|
176 |
Then you can download any individual model file to the current directory, at high speed, with a command like this:
|
177 |
|
178 |
```shell
|
179 |
-
huggingface-cli download TheBloke/medalpaca-13B-GGUF medalpaca-13b.
|
180 |
```
|
181 |
|
182 |
<details>
|
@@ -199,7 +199,7 @@ pip3 install hf_transfer
|
|
199 |
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
|
200 |
|
201 |
```shell
|
202 |
-
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/medalpaca-13B-GGUF medalpaca-13b.
|
203 |
```
|
204 |
|
205 |
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
|
@@ -212,7 +212,7 @@ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running
|
|
212 |
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
213 |
|
214 |
```shell
|
215 |
-
./main -ngl 32 -m medalpaca-13b.
|
216 |
```
|
217 |
|
218 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
@@ -252,7 +252,7 @@ CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
|
|
252 |
from ctransformers import AutoModelForCausalLM
|
253 |
|
254 |
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
|
255 |
-
llm = AutoModelForCausalLM.from_pretrained("TheBloke/medalpaca-13B-GGUF", model_file="medalpaca-13b.
|
256 |
|
257 |
print(llm("AI is going to"))
|
258 |
```
|
|
|
161 |
|
162 |
### In `text-generation-webui`
|
163 |
|
164 |
+
Under Download Model, you can enter the model repo: TheBloke/medalpaca-13B-GGUF and below it, a specific filename to download, such as: medalpaca-13b.Q4_K_M.gguf.
|
165 |
|
166 |
Then click Download.
|
167 |
|
|
|
176 |
Then you can download any individual model file to the current directory, at high speed, with a command like this:
|
177 |
|
178 |
```shell
|
179 |
+
huggingface-cli download TheBloke/medalpaca-13B-GGUF medalpaca-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
|
180 |
```
|
181 |
|
182 |
<details>
|
|
|
199 |
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
|
200 |
|
201 |
```shell
|
202 |
+
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/medalpaca-13B-GGUF medalpaca-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
|
203 |
```
|
204 |
|
205 |
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
|
|
|
212 |
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
213 |
|
214 |
```shell
|
215 |
+
./main -ngl 32 -m medalpaca-13b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
|
216 |
```
|
217 |
|
218 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
|
|
252 |
from ctransformers import AutoModelForCausalLM
|
253 |
|
254 |
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
|
255 |
+
llm = AutoModelForCausalLM.from_pretrained("TheBloke/medalpaca-13B-GGUF", model_file="medalpaca-13b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
|
256 |
|
257 |
print(llm("AI is going to"))
|
258 |
```
|