Upload README.md
Browse files
README.md
CHANGED
@@ -47,7 +47,7 @@ This repo contains GGUF format model files for [Eric Hartford's WizardLM-13b-V1.
|
|
47 |
<!-- README_GGUF.md-about-gguf start -->
|
48 |
### About GGUF
|
49 |
|
50 |
-
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
|
51 |
|
52 |
Here is an incomplate list of clients and libraries that are known to support GGUF:
|
53 |
|
@@ -85,7 +85,7 @@ A chat between a curious user and an artificial intelligence assistant. The assi
|
|
85 |
<!-- compatibility_gguf start -->
|
86 |
## Compatibility
|
87 |
|
88 |
-
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [
|
89 |
|
90 |
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
|
91 |
|
@@ -149,7 +149,7 @@ Then click Download.
|
|
149 |
I recommend using the `huggingface-hub` Python library:
|
150 |
|
151 |
```shell
|
152 |
-
pip3 install huggingface-hub
|
153 |
```
|
154 |
|
155 |
Then you can download any individual model file to the current directory, at high speed, with a command like this:
|
@@ -178,25 +178,25 @@ pip3 install hf_transfer
|
|
178 |
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
|
179 |
|
180 |
```shell
|
181 |
-
|
182 |
```
|
183 |
|
184 |
-
Windows
|
185 |
</details>
|
186 |
<!-- README_GGUF.md-how-to-download end -->
|
187 |
|
188 |
<!-- README_GGUF.md-how-to-run start -->
|
189 |
## Example `llama.cpp` command
|
190 |
|
191 |
-
Make sure you are using `llama.cpp` from commit [
|
192 |
|
193 |
```shell
|
194 |
-
./main -ngl 32 -m wizardlm-13b-v1.0-uncensored.Q4_K_M.gguf --color -c
|
195 |
```
|
196 |
|
197 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
198 |
|
199 |
-
Change `-c
|
200 |
|
201 |
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
|
202 |
|
@@ -210,22 +210,24 @@ Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://git
|
|
210 |
|
211 |
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
|
212 |
|
213 |
-
### How to load this model
|
214 |
|
215 |
#### First install the package
|
216 |
|
217 |
-
|
|
|
|
|
218 |
# Base ctransformers with no GPU acceleration
|
219 |
-
pip install ctransformers
|
220 |
# Or with CUDA GPU acceleration
|
221 |
-
pip install ctransformers[cuda]
|
222 |
-
# Or with ROCm GPU acceleration
|
223 |
-
CT_HIPBLAS=1 pip install ctransformers
|
224 |
-
# Or with Metal GPU acceleration for macOS systems
|
225 |
-
CT_METAL=1 pip install ctransformers
|
226 |
```
|
227 |
|
228 |
-
#### Simple example code
|
229 |
|
230 |
```python
|
231 |
from ctransformers import AutoModelForCausalLM
|
@@ -238,7 +240,7 @@ print(llm("AI is going to"))
|
|
238 |
|
239 |
## How to use with LangChain
|
240 |
|
241 |
-
Here
|
242 |
|
243 |
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
|
244 |
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
@@ -282,6 +284,24 @@ And thank you again to a16z for their generous grant.
|
|
282 |
<!-- original-model-card start -->
|
283 |
# Original model card: Eric Hartford's WizardLM-13b-V1.0-Uncensored
|
284 |
|
285 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
286 |
|
287 |
<!-- original-model-card end -->
|
|
|
47 |
<!-- README_GGUF.md-about-gguf start -->
|
48 |
### About GGUF
|
49 |
|
50 |
+
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
|
51 |
|
52 |
Here is an incomplate list of clients and libraries that are known to support GGUF:
|
53 |
|
|
|
85 |
<!-- compatibility_gguf start -->
|
86 |
## Compatibility
|
87 |
|
88 |
+
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
|
89 |
|
90 |
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
|
91 |
|
|
|
149 |
I recommend using the `huggingface-hub` Python library:
|
150 |
|
151 |
```shell
|
152 |
+
pip3 install huggingface-hub
|
153 |
```
|
154 |
|
155 |
Then you can download any individual model file to the current directory, at high speed, with a command like this:
|
|
|
178 |
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
|
179 |
|
180 |
```shell
|
181 |
+
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/WizardLM-13B-V1.0-Uncensored-GGUF wizardlm-13b-v1.0-uncensored.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
|
182 |
```
|
183 |
|
184 |
+
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
|
185 |
</details>
|
186 |
<!-- README_GGUF.md-how-to-download end -->
|
187 |
|
188 |
<!-- README_GGUF.md-how-to-run start -->
|
189 |
## Example `llama.cpp` command
|
190 |
|
191 |
+
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
192 |
|
193 |
```shell
|
194 |
+
./main -ngl 32 -m wizardlm-13b-v1.0-uncensored.Q4_K_M.gguf --color -c 2048 --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:"
|
195 |
```
|
196 |
|
197 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
198 |
|
199 |
+
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
|
200 |
|
201 |
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
|
202 |
|
|
|
210 |
|
211 |
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
|
212 |
|
213 |
+
### How to load this model in Python code, using ctransformers
|
214 |
|
215 |
#### First install the package
|
216 |
|
217 |
+
Run one of the following commands, according to your system:
|
218 |
+
|
219 |
+
```shell
|
220 |
# Base ctransformers with no GPU acceleration
|
221 |
+
pip install ctransformers
|
222 |
# Or with CUDA GPU acceleration
|
223 |
+
pip install ctransformers[cuda]
|
224 |
+
# Or with AMD ROCm GPU acceleration (Linux only)
|
225 |
+
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
|
226 |
+
# Or with Metal GPU acceleration for macOS systems only
|
227 |
+
CT_METAL=1 pip install ctransformers --no-binary ctransformers
|
228 |
```
|
229 |
|
230 |
+
#### Simple ctransformers example code
|
231 |
|
232 |
```python
|
233 |
from ctransformers import AutoModelForCausalLM
|
|
|
240 |
|
241 |
## How to use with LangChain
|
242 |
|
243 |
+
Here are guides on using llama-cpp-python and ctransformers with LangChain:
|
244 |
|
245 |
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
|
246 |
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
|
|
284 |
<!-- original-model-card start -->
|
285 |
# Original model card: Eric Hartford's WizardLM-13b-V1.0-Uncensored
|
286 |
|
287 |
+
|
288 |
+
This is a retraining of https://huggingface.co/WizardLM/WizardLM-13B-V1.0 with a filtered dataset, intended to reduce refusals, avoidance, and bias.
|
289 |
+
|
290 |
+
Note that LLaMA itself has inherent ethical beliefs, so there's no such thing as a "truly uncensored" model. But this model will be more compliant than WizardLM/WizardLM-7B-V1.0.
|
291 |
+
|
292 |
+
Shout out to the open source AI/ML community, and everyone who helped me out.
|
293 |
+
|
294 |
+
Note: An uncensored model has no guardrails. You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car. Publishing anything this model generates is the same as publishing it yourself. You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
|
295 |
+
|
296 |
+
Like WizardLM/WizardLM-13B-V1.0, this model is trained with Vicuna-1.1 style prompts.
|
297 |
+
|
298 |
+
```
|
299 |
+
You are a helpful AI assistant.
|
300 |
+
|
301 |
+
USER: <prompt>
|
302 |
+
ASSISTANT:
|
303 |
+
```
|
304 |
+
|
305 |
+
Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
|
306 |
|
307 |
<!-- original-model-card end -->
|