Update for Transformers GPTQ support
Browse files- README.md +50 -46
- config.json +34 -23
- gptq_model-3bit--1g.safetensors → model.safetensors +2 -2
- quantize_config.json +1 -1
README.md
CHANGED
@@ -14,17 +14,20 @@ tags:
|
|
14 |
---
|
15 |
|
16 |
<!-- header start -->
|
17 |
-
|
18 |
-
|
|
|
19 |
</div>
|
20 |
<div style="display: flex; justify-content: space-between; width: 100%;">
|
21 |
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
22 |
-
<p><a href="https://discord.gg/theblokeai">Chat & support:
|
23 |
</div>
|
24 |
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
25 |
-
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
|
26 |
</div>
|
27 |
</div>
|
|
|
|
|
28 |
<!-- header end -->
|
29 |
|
30 |
# Meta's Llama 2 70B Chat GPTQ
|
@@ -45,29 +48,39 @@ Now that we have ExLlama, that is the recommended loader to use for these models
|
|
45 |
|
46 |
Reminder: ExLlama does not support 3-bit models, so if you wish to try those quants, you will need to use AutoGPTQ or GPTQ-for-LLaMa.
|
47 |
|
|
|
48 |
|
49 |
-
|
50 |
-
|
51 |
-
If you plan to use any of these quants with AutoGPTQ or GPTQ-for-LLaMa, you will need to update Transformers to the latest Github code:
|
52 |
|
|
|
53 |
```
|
54 |
-
pip3 install
|
55 |
```
|
56 |
|
57 |
-
If using a UI like text-generation-webui, make sure to do this in the Python environment of text-generation-webui.
|
58 |
-
|
59 |
-
|
60 |
## Repositories available
|
61 |
|
62 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-70B-chat-GPTQ)
|
|
|
63 |
* [Original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Llama-2-70B-chat-fp16)
|
64 |
|
65 |
## Prompt template: Llama-2-Chat
|
66 |
|
67 |
```
|
68 |
-
|
69 |
-
|
70 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
```
|
72 |
|
73 |
## Provided files
|
@@ -78,10 +91,10 @@ Each separate quant is in a different branch. See below for instructions on fet
|
|
78 |
|
79 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
80 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
81 |
-
| main | 4 |
|
82 |
-
| gptq-4bit-32g-actorder_True | 4 | 32 | True | 40.66 GB |
|
83 |
-
| gptq-4bit-64g-actorder_True | 4 | 64 | True | 37.99 GB |
|
84 |
-
| gptq-4bit-128g-actorder_True | 4 | 128 | True | 36.65 GB |
|
85 |
| gptq-3bit--1g-actorder_True | 3 | None | True | 26.78 GB | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
|
86 |
| gptq-3bit-128g-actorder_False | 3 | 128 | False | 28.03 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
|
87 |
| gptq-3bit-128g-actorder_True | 3 | 128 | True | 28.03 GB | False | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
|
@@ -92,7 +105,7 @@ Each separate quant is in a different branch. See below for instructions on fet
|
|
92 |
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Llama-2-70B-chat-GPTQ:gptq-4bit-32g-actorder_True`
|
93 |
- With Git, you can clone a branch with:
|
94 |
```
|
95 |
-
git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Llama-2-70B-chat-GPTQ
|
96 |
```
|
97 |
- In Python Transformers code, the branch is the `revision` parameter; see below.
|
98 |
|
@@ -104,23 +117,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
|
|
104 |
|
105 |
### Use ExLlama (4-bit models only) - recommended option if you have enough VRAM for 4-bit
|
106 |
|
107 |
-
ExLlama has now been updated to support Llama 2 70B
|
108 |
-
|
109 |
-
By default text-generation-webui installs a pre-compiled wheel for ExLlama. Until text-generation-webui updates to reflect the ExLlama changes - which hopefully won't be long - you must uninstall that and then clone ExLlama into the `text-generation-webui/repositories` directory. ExLlama will then compile its kernel on model load.
|
110 |
-
|
111 |
-
Note that this requires that your system is capable of compiling CUDA extensions, which may be an issue on Windows.
|
112 |
-
|
113 |
-
Instructions for Linux One Click Installer:
|
114 |
-
|
115 |
-
1. Change directory into the text-generation-webui main folder: `cd /path/to/text-generation-webui`
|
116 |
-
2. Activate the conda env of text-generation-webui:
|
117 |
-
```
|
118 |
-
source "installer_files/conda/etc/profile.d/conda.sh"
|
119 |
-
conda activate installer_files/env
|
120 |
-
```
|
121 |
-
3. Run: `pip3 uninstall exllama`
|
122 |
-
4. Run: `cd repositories/exllama` followed by `git pull` to update exllama.
|
123 |
-
6. Now launch text-generation-webui and follow the instructions below for downloading and running the model. ExLlama should build its kernel when the model first loads.
|
124 |
|
125 |
### Downloading and running the model in text-generation-webui
|
126 |
|
@@ -140,16 +137,16 @@ conda activate installer_files/env
|
|
140 |
|
141 |
## How to use this GPTQ model from Python code
|
142 |
|
143 |
-
First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
|
144 |
|
145 |
```
|
146 |
-
|
147 |
```
|
148 |
|
149 |
You also need the latest Transformers code from Github:
|
150 |
|
151 |
```
|
152 |
-
pip3 install
|
153 |
```
|
154 |
|
155 |
You must set `inject_fused_attention=False` as shown below.
|
@@ -161,7 +158,7 @@ from transformers import AutoTokenizer, pipeline, logging
|
|
161 |
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
|
162 |
|
163 |
model_name_or_path = "TheBloke/Llama-2-70B-chat-GPTQ"
|
164 |
-
model_basename = "
|
165 |
|
166 |
use_triton = False
|
167 |
|
@@ -190,9 +187,12 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
|
|
190 |
"""
|
191 |
|
192 |
prompt = "Tell me about AI"
|
193 |
-
|
194 |
-
|
195 |
-
|
|
|
|
|
|
|
196 |
'''
|
197 |
|
198 |
print("\n\n*** Generate:")
|
@@ -226,9 +226,10 @@ The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLa
|
|
226 |
|
227 |
ExLlama is now compatible with Llama 2 70B models, as of [this commit](https://github.com/turboderp/exllama/commit/b3aea521859b83cfd889c4c00c05a323313b7fee).
|
228 |
|
229 |
-
|
230 |
|
231 |
<!-- footer start -->
|
|
|
232 |
## Discord
|
233 |
|
234 |
For further support, and discussions on these models and AI in general, join us at:
|
@@ -248,12 +249,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
|
|
248 |
* Patreon: https://patreon.com/TheBlokeAI
|
249 |
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
250 |
|
251 |
-
**Special thanks to**:
|
|
|
|
|
252 |
|
253 |
-
**Patreon special mentions**: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang.
|
254 |
|
255 |
Thank you to all my generous patrons and donaters!
|
256 |
|
|
|
|
|
257 |
<!-- footer end -->
|
258 |
|
259 |
# Original model card: Meta's Llama 2 70B Chat
|
|
|
14 |
---
|
15 |
|
16 |
<!-- header start -->
|
17 |
+
<!-- 200823 -->
|
18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
19 |
+
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
20 |
</div>
|
21 |
<div style="display: flex; justify-content: space-between; width: 100%;">
|
22 |
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
23 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
|
24 |
</div>
|
25 |
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
26 |
+
<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>
|
27 |
</div>
|
28 |
</div>
|
29 |
+
<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>
|
30 |
+
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
31 |
<!-- header end -->
|
32 |
|
33 |
# Meta's Llama 2 70B Chat GPTQ
|
|
|
48 |
|
49 |
Reminder: ExLlama does not support 3-bit models, so if you wish to try those quants, you will need to use AutoGPTQ or GPTQ-for-LLaMa.
|
50 |
|
51 |
+
## AutoGPTQ and GPTQ-for-LLaMa compatibility
|
52 |
|
53 |
+
Please update AutoGPTQ to version 0.3.1 or later. This will also update Transformers to 4.31.0, which is required for Llama 70B compatibility.
|
|
|
|
|
54 |
|
55 |
+
If you're using GPTQ-for-LLaMa, please update Transformers manually with:
|
56 |
```
|
57 |
+
pip3 install "transformers>=4.31.0"
|
58 |
```
|
59 |
|
|
|
|
|
|
|
60 |
## Repositories available
|
61 |
|
62 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-70B-chat-GPTQ)
|
63 |
+
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference.](https://huggingface.co/TheBloke/Llama-2-70B-chat-GGML)
|
64 |
* [Original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Llama-2-70B-chat-fp16)
|
65 |
|
66 |
## Prompt template: Llama-2-Chat
|
67 |
|
68 |
```
|
69 |
+
[INST] <<SYS>>
|
70 |
+
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
|
71 |
+
<</SYS>>
|
72 |
+
|
73 |
+
{prompt} [/INST]
|
74 |
+
```
|
75 |
+
|
76 |
+
To continue a conversation:
|
77 |
+
|
78 |
+
```
|
79 |
+
[INST] <<SYS>>
|
80 |
+
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
|
81 |
+
<</SYS>>
|
82 |
+
|
83 |
+
{prompt} [/INST] {model_reply} [INST] {prompt} [/INST]
|
84 |
```
|
85 |
|
86 |
## Provided files
|
|
|
91 |
|
92 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
93 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
94 |
+
| main | 4 | -1 | True | 35.33 GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
|
95 |
+
| gptq-4bit-32g-actorder_True | 4 | 32 | True | 40.66 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
|
96 |
+
| gptq-4bit-64g-actorder_True | 4 | 64 | True | 37.99 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
|
97 |
+
| gptq-4bit-128g-actorder_True | 4 | 128 | True | 36.65 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
|
98 |
| gptq-3bit--1g-actorder_True | 3 | None | True | 26.78 GB | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
|
99 |
| gptq-3bit-128g-actorder_False | 3 | 128 | False | 28.03 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
|
100 |
| gptq-3bit-128g-actorder_True | 3 | 128 | True | 28.03 GB | False | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
|
|
|
105 |
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Llama-2-70B-chat-GPTQ:gptq-4bit-32g-actorder_True`
|
106 |
- With Git, you can clone a branch with:
|
107 |
```
|
108 |
+
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Llama-2-70B-chat-GPTQ
|
109 |
```
|
110 |
- In Python Transformers code, the branch is the `revision` parameter; see below.
|
111 |
|
|
|
117 |
|
118 |
### Use ExLlama (4-bit models only) - recommended option if you have enough VRAM for 4-bit
|
119 |
|
120 |
+
ExLlama has now been updated to support Llama 2 70B. Make sure you're using the latest version of ExLlama, and text-generation-webui if you're using that.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
121 |
|
122 |
### Downloading and running the model in text-generation-webui
|
123 |
|
|
|
137 |
|
138 |
## How to use this GPTQ model from Python code
|
139 |
|
140 |
+
First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed, version 0.3.1 or 0.3.2 or later:
|
141 |
|
142 |
```
|
143 |
+
pip3 install auto-gptq
|
144 |
```
|
145 |
|
146 |
You also need the latest Transformers code from Github:
|
147 |
|
148 |
```
|
149 |
+
pip3 install "transformers>=4.31.0"
|
150 |
```
|
151 |
|
152 |
You must set `inject_fused_attention=False` as shown below.
|
|
|
158 |
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
|
159 |
|
160 |
model_name_or_path = "TheBloke/Llama-2-70B-chat-GPTQ"
|
161 |
+
model_basename = "model"
|
162 |
|
163 |
use_triton = False
|
164 |
|
|
|
187 |
"""
|
188 |
|
189 |
prompt = "Tell me about AI"
|
190 |
+
system_message = "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."
|
191 |
+
prompt_template=f'''[INST] <<SYS>>
|
192 |
+
{system_message}
|
193 |
+
<</SYS>>
|
194 |
+
|
195 |
+
{prompt} [/INST]
|
196 |
'''
|
197 |
|
198 |
print("\n\n*** Generate:")
|
|
|
226 |
|
227 |
ExLlama is now compatible with Llama 2 70B models, as of [this commit](https://github.com/turboderp/exllama/commit/b3aea521859b83cfd889c4c00c05a323313b7fee).
|
228 |
|
229 |
+
Please see the Provided Files table above for per-file compatibility.
|
230 |
|
231 |
<!-- footer start -->
|
232 |
+
<!-- 200823 -->
|
233 |
## Discord
|
234 |
|
235 |
For further support, and discussions on these models and AI in general, join us at:
|
|
|
249 |
* Patreon: https://patreon.com/TheBlokeAI
|
250 |
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
251 |
|
252 |
+
**Special thanks to**: Aemon Algiz.
|
253 |
+
|
254 |
+
**Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
|
255 |
|
|
|
256 |
|
257 |
Thank you to all my generous patrons and donaters!
|
258 |
|
259 |
+
And thank you again to a16z for their generous grant.
|
260 |
+
|
261 |
<!-- footer end -->
|
262 |
|
263 |
# Original model card: Meta's Llama 2 70B Chat
|
config.json
CHANGED
@@ -1,25 +1,36 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 1,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"hidden_act": "silu",
|
8 |
+
"hidden_size": 8192,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 28672,
|
11 |
+
"max_position_embeddings": 2048,
|
12 |
+
"model_type": "llama",
|
13 |
+
"num_attention_heads": 64,
|
14 |
+
"num_hidden_layers": 80,
|
15 |
+
"num_key_value_heads": 8,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"pretraining_tp": 1,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.32.0.dev0",
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 32000,
|
25 |
+
"quantization_config": {
|
26 |
+
"bits": 3,
|
27 |
+
"group_size": -1,
|
28 |
+
"damp_percent": 0.01,
|
29 |
+
"desc_act": true,
|
30 |
+
"sym": true,
|
31 |
+
"true_sequential": true,
|
32 |
+
"model_name_or_path": null,
|
33 |
+
"model_file_base_name": "model",
|
34 |
+
"quant_method": "gptq"
|
35 |
+
}
|
36 |
}
|
gptq_model-3bit--1g.safetensors → model.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e393530c0949942d18e5a5f924bc9ec2ce9c38e6e218884dc64d7eefae2650f2
|
3 |
+
size 26775011232
|
quantize_config.json
CHANGED
@@ -6,5 +6,5 @@
|
|
6 |
"sym": true,
|
7 |
"true_sequential": true,
|
8 |
"model_name_or_path": null,
|
9 |
-
"model_file_base_name":
|
10 |
}
|
|
|
6 |
"sym": true,
|
7 |
"true_sequential": true,
|
8 |
"model_name_or_path": null,
|
9 |
+
"model_file_base_name": "model"
|
10 |
}
|