TheBloke commited on
Commit
7008295
1 Parent(s): 0e09acb

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +490 -0
README.md ADDED
@@ -0,0 +1,490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: LLM360/AmberChat
3
+ datasets:
4
+ - WizardLM/WizardLM_evol_instruct_V2_196k
5
+ - icybee/share_gpt_90k_v1
6
+ inference: false
7
+ language:
8
+ - en
9
+ library_name: transformers
10
+ license: apache-2.0
11
+ model_creator: LLM360
12
+ model_name: AmberChat
13
+ model_type: amber
14
+ pipeline_tag: text-generation
15
+ prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
16
+ The assistant gives helpful, detailed, and polite answers to the user''s questions.
17
+ USER: {prompt} ASSISTANT:
18
+
19
+ '
20
+ quantized_by: TheBloke
21
+ tags:
22
+ - nlp
23
+ - llm
24
+ widget:
25
+ - example_title: example 1
26
+ output:
27
+ text: "Mounting a TV to drywall safely is crucial to ensure the longevity of your\
28
+ \ TV and the wall. Here's a step-by-step guide on how to do it safely:\n 1.\
29
+ \ Choose the right mount: Choose a mount that is compatible with your TV and\
30
+ \ the wall. Make sure the mount is rated for drywall and not just wood or concrete.\n\
31
+ \ 2. Prepare the wall: Before mounting the TV, make sure the wall is clean and\
32
+ \ free from any debris or paint. Use a stud finder to locate the studs in the\
33
+ \ wall.\n 3. Install the mount: Follow the manufacturer's instructions for mounting\
34
+ \ the TV to the wall. Use appropriate hardware and tools to secure the mount\
35
+ \ to the wall.\n 4. Level the TV: Level the TV on the mount using a spirit level\
36
+ \ or a leveling kit provided by the mount manufacturer.\n 5. Attach the TV to\
37
+ \ the mount: Attach the TV to the mount using the appropriate hardware and tools.\
38
+ \ Tighten the bolts and screws to ensure the TV is securely attached.\n 6. Connect\
39
+ \ the cables: Connect the TV cables to the appropriate ports on the back of\
40
+ \ the TV and the mount.\n 7. Test the mount: Test the mount to ensure it's secure\
41
+ \ and stable. Adjust the mount as needed to ensure the TV is level and secure.\n\
42
+ \ Mounting a TV to drywall safely is crucial to avoid damaging the wall or the\
43
+ \ TV. Follow these steps carefully and use appropriate tools and hardware to\
44
+ \ ensure a secure and stable installation."
45
+ text: How do I mount a tv to drywall safely?
46
+ - example_title: example 2
47
+ output:
48
+ text: The adjective that can be used to describe the opposite of calm is "anxious"
49
+ or "stressed." So, from happy to sad, we can say that happy is to sad as calm
50
+ is to anxious or stressed.
51
+ text: Happy is to sad as calm is to _.
52
+ ---
53
+ <!-- markdownlint-disable MD041 -->
54
+
55
+ <!-- header start -->
56
+ <!-- 200823 -->
57
+ <div style="width: auto; margin-left: auto; margin-right: auto">
58
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
59
+ </div>
60
+ <div style="display: flex; justify-content: space-between; width: 100%;">
61
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
62
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
63
+ </div>
64
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
65
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
66
+ </div>
67
+ </div>
68
+ <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
69
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
70
+ <!-- header end -->
71
+
72
+ # AmberChat - GPTQ
73
+ - Model creator: [LLM360](https://huggingface.co/LLM360)
74
+ - Original model: [AmberChat](https://huggingface.co/LLM360/AmberChat)
75
+
76
+ <!-- description start -->
77
+ # Description
78
+
79
+ This repo contains GPTQ model files for [LLM360's AmberChat](https://huggingface.co/LLM360/AmberChat).
80
+
81
+ Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
82
+
83
+ These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
84
+
85
+ <!-- description end -->
86
+ <!-- repositories-available start -->
87
+ ## Repositories available
88
+
89
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/AmberChat-AWQ)
90
+ * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/AmberChat-GPTQ)
91
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/AmberChat-GGUF)
92
+ * [LLM360's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/LLM360/AmberChat)
93
+ <!-- repositories-available end -->
94
+
95
+ <!-- prompt-template start -->
96
+ ## Prompt template: Vicuna
97
+
98
+ ```
99
+ 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:
100
+
101
+ ```
102
+
103
+ <!-- prompt-template end -->
104
+
105
+
106
+
107
+ <!-- README_GPTQ.md-compatible clients start -->
108
+ ## Known compatible clients / servers
109
+
110
+ GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
111
+
112
+ These GPTQ models are known to work in the following inference servers/webuis.
113
+
114
+ - [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
115
+ - [KoboldAI United](https://github.com/henk717/koboldai)
116
+ - [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
117
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
118
+
119
+ This may not be a complete list; if you know of others, please let me know!
120
+ <!-- README_GPTQ.md-compatible clients end -->
121
+
122
+ <!-- README_GPTQ.md-provided-files start -->
123
+ ## Provided files, and GPTQ parameters
124
+
125
+ Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
126
+
127
+ Each separate quant is in a different branch. See below for instructions on fetching from different branches.
128
+
129
+ Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
130
+
131
+ <details>
132
+ <summary>Explanation of GPTQ parameters</summary>
133
+
134
+ - Bits: The bit size of the quantised model.
135
+ - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
136
+ - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
137
+ - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
138
+ - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
139
+ - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
140
+ - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
141
+
142
+ </details>
143
+
144
+ | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
145
+ | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
146
+ | [main](https://huggingface.co/TheBloke/AmberChat-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 3.90 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
147
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/AmberChat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 4.28 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
148
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/AmberChat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
149
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/AmberChat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
150
+ | [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/AmberChat-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 7.62 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
151
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/AmberChat-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 4.02 GB | No | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
152
+
153
+ <!-- README_GPTQ.md-provided-files end -->
154
+
155
+ <!-- README_GPTQ.md-download-from-branches start -->
156
+ ## How to download, including from branches
157
+
158
+ ### In text-generation-webui
159
+
160
+ To download from the `main` branch, enter `TheBloke/AmberChat-GPTQ` in the "Download model" box.
161
+
162
+ To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/AmberChat-GPTQ:gptq-4bit-32g-actorder_True`
163
+
164
+ ### From the command line
165
+
166
+ I recommend using the `huggingface-hub` Python library:
167
+
168
+ ```shell
169
+ pip3 install huggingface-hub
170
+ ```
171
+
172
+ To download the `main` branch to a folder called `AmberChat-GPTQ`:
173
+
174
+ ```shell
175
+ mkdir AmberChat-GPTQ
176
+ huggingface-cli download TheBloke/AmberChat-GPTQ --local-dir AmberChat-GPTQ --local-dir-use-symlinks False
177
+ ```
178
+
179
+ To download from a different branch, add the `--revision` parameter:
180
+
181
+ ```shell
182
+ mkdir AmberChat-GPTQ
183
+ huggingface-cli download TheBloke/AmberChat-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir AmberChat-GPTQ --local-dir-use-symlinks False
184
+ ```
185
+
186
+ <details>
187
+ <summary>More advanced huggingface-cli download usage</summary>
188
+
189
+ If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
190
+
191
+ The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
192
+
193
+ For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
194
+
195
+ To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
196
+
197
+ ```shell
198
+ pip3 install hf_transfer
199
+ ```
200
+
201
+ And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
202
+
203
+ ```shell
204
+ mkdir AmberChat-GPTQ
205
+ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/AmberChat-GPTQ --local-dir AmberChat-GPTQ --local-dir-use-symlinks False
206
+ ```
207
+
208
+ Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
209
+ </details>
210
+
211
+ ### With `git` (**not** recommended)
212
+
213
+ To clone a specific branch with `git`, use a command like this:
214
+
215
+ ```shell
216
+ git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/AmberChat-GPTQ
217
+ ```
218
+
219
+ Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
220
+
221
+ <!-- README_GPTQ.md-download-from-branches end -->
222
+ <!-- README_GPTQ.md-text-generation-webui start -->
223
+ ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
224
+
225
+ Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
226
+
227
+ It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
228
+
229
+ 1. Click the **Model tab**.
230
+ 2. Under **Download custom model or LoRA**, enter `TheBloke/AmberChat-GPTQ`.
231
+
232
+ - To download from a specific branch, enter for example `TheBloke/AmberChat-GPTQ:gptq-4bit-32g-actorder_True`
233
+ - see Provided Files above for the list of branches for each option.
234
+
235
+ 3. Click **Download**.
236
+ 4. The model will start downloading. Once it's finished it will say "Done".
237
+ 5. In the top left, click the refresh icon next to **Model**.
238
+ 6. In the **Model** dropdown, choose the model you just downloaded: `AmberChat-GPTQ`
239
+ 7. The model will automatically load, and is now ready for use!
240
+ 8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
241
+
242
+ - Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
243
+
244
+ 9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
245
+
246
+ <!-- README_GPTQ.md-text-generation-webui end -->
247
+
248
+ <!-- README_GPTQ.md-use-from-tgi start -->
249
+ ## Serving this model from Text Generation Inference (TGI)
250
+
251
+ It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
252
+
253
+ Example Docker parameters:
254
+
255
+ ```shell
256
+ --model-id TheBloke/AmberChat-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
257
+ ```
258
+
259
+ Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
260
+
261
+ ```shell
262
+ pip3 install huggingface-hub
263
+ ```
264
+
265
+ ```python
266
+ from huggingface_hub import InferenceClient
267
+
268
+ endpoint_url = "https://your-endpoint-url-here"
269
+
270
+ prompt = "Tell me about AI"
271
+ prompt_template=f'''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:
272
+ '''
273
+
274
+ client = InferenceClient(endpoint_url)
275
+ response = client.text_generation(prompt,
276
+ max_new_tokens=128,
277
+ do_sample=True,
278
+ temperature=0.7,
279
+ top_p=0.95,
280
+ top_k=40,
281
+ repetition_penalty=1.1)
282
+
283
+ print(f"Model output: {response}")
284
+ ```
285
+ <!-- README_GPTQ.md-use-from-tgi end -->
286
+ <!-- README_GPTQ.md-use-from-python start -->
287
+ ## Python code example: inference from this GPTQ model
288
+
289
+ ### Install the necessary packages
290
+
291
+ Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
292
+
293
+ ```shell
294
+ pip3 install --upgrade transformers optimum
295
+ # If using PyTorch 2.1 + CUDA 12.x:
296
+ pip3 install --upgrade auto-gptq
297
+ # or, if using PyTorch 2.1 + CUDA 11.x:
298
+ pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
299
+ ```
300
+
301
+ If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
302
+
303
+ ```shell
304
+ pip3 uninstall -y auto-gptq
305
+ git clone https://github.com/PanQiWei/AutoGPTQ
306
+ cd AutoGPTQ
307
+ git checkout v0.5.1
308
+ pip3 install .
309
+ ```
310
+
311
+ ### Example Python code
312
+
313
+ ```python
314
+ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
315
+
316
+ model_name_or_path = "TheBloke/AmberChat-GPTQ"
317
+ # To use a different branch, change revision
318
+ # For example: revision="gptq-4bit-32g-actorder_True"
319
+ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
320
+ device_map="auto",
321
+ trust_remote_code=False,
322
+ revision="main")
323
+
324
+ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
325
+
326
+ prompt = "Tell me about AI"
327
+ prompt_template=f'''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:
328
+ '''
329
+
330
+ print("\n\n*** Generate:")
331
+
332
+ input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
333
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
334
+ print(tokenizer.decode(output[0]))
335
+
336
+ # Inference can also be done using transformers' pipeline
337
+
338
+ print("*** Pipeline:")
339
+ pipe = pipeline(
340
+ "text-generation",
341
+ model=model,
342
+ tokenizer=tokenizer,
343
+ max_new_tokens=512,
344
+ do_sample=True,
345
+ temperature=0.7,
346
+ top_p=0.95,
347
+ top_k=40,
348
+ repetition_penalty=1.1
349
+ )
350
+
351
+ print(pipe(prompt_template)[0]['generated_text'])
352
+ ```
353
+ <!-- README_GPTQ.md-use-from-python end -->
354
+
355
+ <!-- README_GPTQ.md-compatibility start -->
356
+ ## Compatibility
357
+
358
+ The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
359
+
360
+ [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
361
+
362
+ For a list of clients/servers, please see "Known compatible clients / servers", above.
363
+ <!-- README_GPTQ.md-compatibility end -->
364
+
365
+ <!-- footer start -->
366
+ <!-- 200823 -->
367
+ ## Discord
368
+
369
+ For further support, and discussions on these models and AI in general, join us at:
370
+
371
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
372
+
373
+ ## Thanks, and how to contribute
374
+
375
+ Thanks to the [chirper.ai](https://chirper.ai) team!
376
+
377
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
378
+
379
+ I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
380
+
381
+ If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
382
+
383
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
384
+
385
+ * Patreon: https://patreon.com/TheBlokeAI
386
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
387
+
388
+ **Special thanks to**: Aemon Algiz.
389
+
390
+ **Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
391
+
392
+
393
+ Thank you to all my generous patrons and donaters!
394
+
395
+ And thank you again to a16z for their generous grant.
396
+
397
+ <!-- footer end -->
398
+
399
+ # Original model card: LLM360's AmberChat
400
+
401
+ # AmberChat
402
+
403
+
404
+ We present AmberChat, an instruction following model finetuned from [LLM360/Amber](https://huggingface.co/LLM360/Amber).
405
+
406
+ ## Model Description
407
+
408
+ - **Model type:** Language model with the same architecture as LLaMA-7B
409
+ - **Language(s) (NLP):** English
410
+ - **License:** Apache 2.0
411
+ - **Resources for more information:**
412
+ - [Metrics](https://github.com/LLM360/Analysis360)
413
+ - [Fully processed Amber pretraining data](https://huggingface.co/datasets/LLM360/AmberDatasets)
414
+
415
+
416
+ # Loading AmberChat
417
+
418
+ ```python
419
+ import torch
420
+ from transformers import LlamaTokenizer, LlamaForCausalLM
421
+
422
+ tokenizer = LlamaTokenizer.from_pretrained("LLM360/AmberChat")
423
+ model = LlamaForCausalLM.from_pretrained("LLM360/AmberChat")
424
+
425
+ #template adapated from fastchat
426
+ template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.\nRemember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!\n### Human: {prompt}\n### Assistant:"
427
+
428
+ prompt = "How do I mount a tv to drywall safely?"
429
+
430
+ input_str = template.format(prompt=prompt)
431
+ input_ids = tokenizer(input_str, return_tensors="pt").input_ids
432
+ outputs = model.generate(input_ids, max_length=1000)
433
+ print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())
434
+ ```
435
+
436
+ Alternatively, you may use [FastChat](https://github.com/lm-sys/FastChat):
437
+ ```bash
438
+ python3 -m fastchat.serve.cli --model-path LLM360/AmberChat
439
+ ```
440
+
441
+ # AmberChat Finetuning Details
442
+
443
+ ## DataMix
444
+ | Subset | Number of rows | License |
445
+ | ----------- | ----------- | ----------- |
446
+ | WizardLM/WizardLM_evol_instruct_V2_196k | 143k | |
447
+ | icybee/share_gpt_90k_v1 | 90k | cc0-1.0 |
448
+ | Total | 233k | |
449
+
450
+ ## Hyperparameters
451
+ | Hyperparameter | Value |
452
+ | ----------- | ----------- |
453
+ | Total Parameters | 6.7B |
454
+ | Hidden Size | 4096 |
455
+ | Intermediate Size (MLPs) | 11008 |
456
+ | Number of Attention Heads | 32 |
457
+ | Number of Hidden Lyaers | 32 |
458
+ | RMSNorm ɛ | 1e^-6 |
459
+ | Max Seq Length | 2048 |
460
+ | Vocab Size | 32000 |
461
+
462
+ | Training Hyperparameter | Value |
463
+ | ----------- | ----------- |
464
+ | learning_rate | 2e-5 |
465
+ | num_train_epochs | 3 |
466
+ | per_device_train_batch_size | 2 |
467
+ | gradient_accumulation_steps | 16 |
468
+ | warmup_ratio | 0.04 |
469
+ | model_max_length | 2048 |
470
+
471
+
472
+ # Evaluation
473
+
474
+ | Model | MT-Bench |
475
+ |------------------------------------------------------|------------------------------------------------------------|
476
+ | LLM360/Amber 359 | 2.48750 |
477
+ | **LLM360/AmberChat** | **5.428125** |
478
+
479
+ # Citation
480
+
481
+ **BibTeX:**
482
+
483
+ ```bibtex
484
+ @article{xxx,
485
+ title={XXX},
486
+ author={XXX},
487
+ journal={XXX},
488
+ year={2023}
489
+ }
490
+ ```