koreallmdev commited on
Commit
c33b9b7
·
verified ·
1 Parent(s): 22c4858

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +26 -19
README.md CHANGED
@@ -4,6 +4,7 @@ pipeline_tag: text-generation
4
  tags:
5
  - qwen
6
  - qwen2
 
7
  - lora
8
  - vllm
9
  - open-webui
@@ -11,21 +12,27 @@ tags:
11
  - coding
12
  ---
13
 
14
- # 7bcustom-model
15
 
16
- This is a public deployment package for a local DGX AI Factory coding assistant runtime.
 
 
 
 
 
 
 
 
17
 
18
  ## Model
19
 
20
- - Public name: `7bcustom-model`
21
  - Runtime served name: `dgx-stable-current`
22
- - Base family: Qwen2 7B Instruct class
23
  - Runtime: vLLM OpenAI-compatible API
24
  - Open-WebUI compatible: yes
25
 
26
- ## Deployment status
27
-
28
- This public release is based on the locally validated stable deployment.
29
 
30
  ```text
31
  average_score: 97.75
@@ -35,21 +42,12 @@ critical_fail_count: 0
35
  decision: DEPLOY_CANDIDATE
36
  ```
37
 
38
- ## Runtime policy
39
-
40
- The local production runtime uses router/template safeguards for deterministic operational answers:
41
-
42
- - Linux guarded prompt
43
- - vLLM medium prompt
44
- - CUDA check template
45
- - LoRA/stable/rejected policy template
46
-
47
  ## vLLM example
48
 
49
  ```bash
50
  python -m vllm.entrypoints.openai.api_server \
51
  --model ./ \
52
- --served-model-name 7bcustom-model \
53
  --dtype float16 \
54
  --host 0.0.0.0 \
55
  --port 8000 \
@@ -62,10 +60,19 @@ python -m vllm.entrypoints.openai.api_server \
62
 
63
  ```text
64
  Base URL: http://<host>:8000/v1
65
- Model : 7bcustom-model
66
  API Key : dummy
67
  ```
68
 
 
 
 
 
 
 
 
 
 
69
  ## Notes
70
 
71
- This repository is intended as a public model/runtime release record. Local absolute paths, private operational logs, and preservation tarballs are not required for public usage.
 
4
  tags:
5
  - qwen
6
  - qwen2
7
+ - 8b
8
  - lora
9
  - vllm
10
  - open-webui
 
12
  - coding
13
  ---
14
 
15
+ # 8bcustom-model
16
 
17
+ This is the public model/runtime release for the DGX AI Factory stable coding assistant.
18
+
19
+ ## Correction notice
20
+
21
+ The previous public repository name used `7bcustom-model`, but the checked model size/name should be treated as **8B-class** for this public title. This repository uses the corrected title:
22
+
23
+ ```text
24
+ 8bcustom-model
25
+ ```
26
 
27
  ## Model
28
 
29
+ - Public name: `8bcustom-model`
30
  - Runtime served name: `dgx-stable-current`
31
+ - Model class: 8B-class local custom coding assistant
32
  - Runtime: vLLM OpenAI-compatible API
33
  - Open-WebUI compatible: yes
34
 
35
+ ## Deployment benchmark
 
 
36
 
37
  ```text
38
  average_score: 97.75
 
42
  decision: DEPLOY_CANDIDATE
43
  ```
44
 
 
 
 
 
 
 
 
 
 
45
  ## vLLM example
46
 
47
  ```bash
48
  python -m vllm.entrypoints.openai.api_server \
49
  --model ./ \
50
+ --served-model-name 8bcustom-model \
51
  --dtype float16 \
52
  --host 0.0.0.0 \
53
  --port 8000 \
 
60
 
61
  ```text
62
  Base URL: http://<host>:8000/v1
63
+ Model : 8bcustom-model
64
  API Key : dummy
65
  ```
66
 
67
+ ## Runtime policy
68
+
69
+ The local production runtime used router/template safeguards for deterministic operational answers:
70
+
71
+ - Linux guarded prompt
72
+ - vLLM medium prompt
73
+ - CUDA check template
74
+ - LoRA/stable/rejected policy template
75
+
76
  ## Notes
77
 
78
+ This public repository is a model/runtime release record. Private preservation archives and local absolute-path operational records are not required for public usage.