lixc99 commited on
Commit
43be10c
·
verified ·
1 Parent(s): bf0d4c7

Add files using upload-large-folder tool

Browse files
README.md CHANGED
@@ -6,7 +6,7 @@ language:
6
  pipeline_tag: text-generation
7
  tags:
8
  - ERNIE4.5
9
- ---
10
 
11
  <div align="center" style="line-height: 1;">
12
  <a href="https://ernie.baidu.com/" target="_blank" style="margin: 2px;">
@@ -95,15 +95,16 @@ python -m fastdeploy.entrypoints.openai.api_server \
95
  --max-num-seqs 32
96
  ```
97
 
98
- To deploy the wint2 TP4 quantized version using FastDeploy, you can run the following command.
 
99
 
100
  ```bash
101
  python -m fastdeploy.entrypoints.openai.api_server \
102
- --model "baidu/ERNIE-4.5-300B-A47B-2Bits-TP4-Paddle" \
103
  --port 8180 \
104
  --metrics-port 8181 \
105
  --engine-worker-queue-port 8182 \
106
- --tensor-parallel-size 4 \
107
  --max-model-len 32768 \
108
  --max-num-seqs 128
109
  ```
@@ -184,8 +185,8 @@ Here are the current time and the references:
184
 
185
  ---------
186
  Please note:
187
- 1. Based on the question’s requirements and the current time, assess the usefulness of the references to avoid using inaccurate or outdated information in the answer.
188
- 2. If the references do not provide enough information to accurately answer the question, you should suggest how to obtain the relevant information or acknowledge that you are unable to provide it.
189
  3. Prioritize using information from highly authoritative sources such as encyclopedias, official websites, authoritative institutions, and professional websites when answering questions.
190
  4. Incorporate relevant numbers, cases, legal provisions, formulas, and other details from the references to make your answer more professional.
191
  5. For creative tasks, keep these dimensions in mind:
@@ -194,7 +195,7 @@ Please note:
194
  - Well-reasoned: Rigorous logic and progressive, combined with authoritative data/facts to support the argument
195
 
196
  ---------
197
- Now, using the information above, answer the question and complete the conversation:
198
  {question}'''
199
  ```
200
 
@@ -234,4 +235,4 @@ If you find ERNIE 4.5 useful or wish to use it in your projects, please kindly c
234
  primaryClass={cs.CL},
235
  url={}
236
  }
237
- ```
 
6
  pipeline_tag: text-generation
7
  tags:
8
  - ERNIE4.5
9
+ ---s
10
 
11
  <div align="center" style="line-height: 1;">
12
  <a href="https://ernie.baidu.com/" target="_blank" style="margin: 2px;">
 
95
  --max-num-seqs 32
96
  ```
97
 
98
+ To deploy the WINT2 quantized version using FastDeploy on two 80G GPUs, run the following command.
99
+
100
 
101
  ```bash
102
  python -m fastdeploy.entrypoints.openai.api_server \
103
+ --model "baidu/ERNIE-4.5-300B-A47B-2Bits-TP2-Paddle" \
104
  --port 8180 \
105
  --metrics-port 8181 \
106
  --engine-worker-queue-port 8182 \
107
+ --tensor-parallel-size 2 \
108
  --max-model-len 32768 \
109
  --max-num-seqs 128
110
  ```
 
185
 
186
  ---------
187
  Please note:
188
+ 1. Based on the question’s requirements and the current time, assess the usefulness of the references to avoid using inaccurate or outdated information in the answer.
189
+ 2. If the references do not provide enough information to accurately answer the question, you should suggest how to obtain the relevant information or acknowledge that you are unable to provide it.
190
  3. Prioritize using information from highly authoritative sources such as encyclopedias, official websites, authoritative institutions, and professional websites when answering questions.
191
  4. Incorporate relevant numbers, cases, legal provisions, formulas, and other details from the references to make your answer more professional.
192
  5. For creative tasks, keep these dimensions in mind:
 
195
  - Well-reasoned: Rigorous logic and progressive, combined with authoritative data/facts to support the argument
196
 
197
  ---------
198
+ Now, using the information above, answer the question and complete the conversation:
199
  {question}'''
200
  ```
201
 
 
235
  primaryClass={cs.CL},
236
  url={}
237
  }
238
+ ```
rank0/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba285a02918edff3336bfb33e2217451ecff5e324920a9cad3a71c891f053c6a
3
+ size 9998013552
rank0/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b357c27eda1bf867c2fac661f7e51c95bb0e8bf4cede49860ae95aba2d11a2c
3
+ size 10001901464
rank0/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488b6693a209ffb4b1b27df62f4b5306882fc918c6c580b9776d678c7d888305
3
+ size 3728826736
rank0/model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
rank1/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1bbefc41f3831f154b452f568c392019266416be09eea04f3e6414c2fad3afe
3
+ size 9998013552
rank1/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd1e0b0a03b0113502b2d0d66f521685d77552918927537e9a8f2762e3cfb7c
3
+ size 10001901464
rank1/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaeeeaf30c495e59f9eff87501e1b7bdfee0421253377a02fd5309cb9c549f3e
3
+ size 3728826736
rank1/model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
rank2/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5d01446431adf3e8c3f68e24fb3faa5caa40a5474b9836447fe4a49e336341
3
+ size 9998013552
rank2/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0c13069564645707654f1cb2000cd2318f4f45112389685bf21ce1732a30eb
3
+ size 10001901464
rank2/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59ac31beea2089daf797ef55e09620ce4911700ca64c6e59d24e46f30b88fb0
3
+ size 3728826736
rank2/model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
rank3/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf97afbad7ee7158f1f706e905283f3e97e789f2657d1d8b51e342d61047d6de
3
+ size 9998013552
rank3/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8760ecf84b11dcb5618c2db6404227207dfcf661e01c65c497d507d32ff7fd4
3
+ size 10001901464
rank3/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:964f12f6609f6d8401ce6d1fc8cb89f7ab3fba186cc8c28d434b07e291282c40
3
+ size 3728826736
rank3/model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff