bartolek lakhera2023 commited on
Commit
80784a8
·
0 Parent(s):

Duplicate from lakhera2023/devops-slm-v1

Browse files

Co-authored-by: Prashant Lakhera <lakhera2023@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - devops
5
+ - kubernetes
6
+ - docker
7
+ - ci-cd
8
+ - infrastructure
9
+ - monitoring
10
+ - specialized
11
+ pipeline_tag: text-generation
12
+ ---
13
+
14
+ # DevOps Specialized Language Model v1
15
+
16
+ ## 🎯 Model Overview
17
+
18
+ This is a **specialized language model** specifically for **DevOps tasks and operations only**.
19
+
20
+ ## ⚠️ Important Notice
21
+
22
+ **This model is designed EXCLUSIVELY for DevOps-related tasks. It has robust filtering that will NOT respond to general questions about movies, weather, cooking, sports, music, travel, health, education, politics, religion, philosophy, entertainment, gaming, fashion, or any non-DevOps topics.**
23
+
24
+ **The model will automatically redirect any non-DevOps questions back to DevOps topics.**
25
+
26
+ ## 🚀 Capabilities
27
+
28
+ The model specializes in:
29
+
30
+ - **Kubernetes Operations**: Deployments, pods, services, troubleshooting
31
+ - **Docker Containerization**: Container management, Dockerfiles, best practices
32
+ - **CI/CD Pipelines**: GitHub Actions, GitLab CI, Jenkins, automation
33
+ - **Infrastructure Automation**: Terraform, Ansible, infrastructure as code
34
+ - **Monitoring & Observability**: Logging, metrics, alerting, performance monitoring
35
+ - **Cloud Platform Operations**: AWS, Azure, GCP, cloud-native solutions
36
+ - **DevOps Tools**: Helm, Prometheus, Grafana, ELK stack, and more
37
+
38
+ ## 🚫 Limitations
39
+
40
+ - **DevOps Only**: Will not respond to non-DevOps questions
41
+ - **Specialized Knowledge**: Focused on DevOps practices and tools
42
+
43
+ ## 💻 Usage
44
+
45
+ ### Basic Usage
46
+
47
+ https://colab.research.google.com/drive/1UgTUI6AeVnSlknHoF3cEDhWLHYirghju?usp=sharing
48
+
49
+ ### Example Queries
50
+
51
+ ✅ **Good DevOps Questions:**
52
+ - "How do I create a Kubernetes deployment?"
53
+ - "What's the difference between Docker and Podman?"
54
+ - "How do I set up a CI/CD pipeline with GitHub Actions?"
55
+ - "How do I troubleshoot a failing Kubernetes pod?"
56
+ - "What are the best practices for container security?"
57
+
58
+ ❌ **Non-DevOps Questions (will be redirected):**
59
+ - "Tell me about movies" → Redirected to DevOps
60
+ - "What's the weather like?" → Redirected to DevOps
61
+ - "Explain quantum physics" → Redirected to DevOps
62
+ - "Write a poem" → Redirected to DevOps
63
+ - "How to cook pasta?" → Redirected to DevOps
64
+ - "Who won the football game?" → Redirected to DevOps
65
+ - "Recommend some music" → Redirected to DevOps
66
+ - "Best travel destinations" → Redirected to DevOps
67
+
68
+ ## 🔧 Technical Details
69
+
70
+ - **Base Model**: lakhera2023/Qwen-model
71
+ - **Architecture**: Transformer-based with LoRA fine-tuning
72
+ - **Training**: DevOps-specific examples
73
+ - **Specialization**: Fine-tuned for DevOps tasks only
74
+
75
+ ## 📊 Performance
76
+
77
+ This model is optimized for:
78
+ - **DevOps Task Accuracy**: High precision on DevOps-related queries
79
+ - **Response Quality**: Clear, actionable DevOps guidance
80
+ - **Topic Focus**: Strict adherence to DevOps-only responses
81
+
82
+ ## 🤝 Contributing
83
+
84
+ This model is specialized for the DevOps community. If you have suggestions for improvements or additional DevOps training data, please open an issue.
85
+
86
+ ## 📄 License
87
+
88
+ This model is released under the Apache 2.0 License.
89
+
90
+ ## ⚠️ Disclaimer
91
+
92
+ This model is designed for educational and professional DevOps use. Always verify any deployment or configuration advice in a safe environment before applying to production systems.
93
+
94
+ ---
95
+
96
+ **Remember: This model is DevOps-only. It will not respond to general questions.**
adapter_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "lakhera2023/Qwen-model",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "down_proj",
29
+ "up_proj",
30
+ "gate_proj",
31
+ "q_proj",
32
+ "v_proj",
33
+ "k_proj",
34
+ "o_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false,
42
+ "model_name": "DevOps-SLM-v1",
43
+ "model_type": "devops_specialized"
44
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d30c7a80215bc335d9888d6eeaed14a5f9341b2eea123d883ef9976cebd24f
3
+ size 73911112
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system
3
+ ' }}
4
+ {%- if messages[0]['role'] == 'system' %}
5
+ {{- messages[0]['content'] }}
6
+ {%- else %}
7
+ {{- 'You are a specialized DevOps assistant. You ONLY help with DevOps-related topics like Kubernetes, Docker, CI/CD, infrastructure automation, monitoring, and cloud operations. If asked about non-DevOps topics (movies, weather, cooking, sports, music, travel, health, education, politics, religion, philosophy, entertainment, gaming, fashion, or any other non-DevOps topics), you MUST politely refuse and redirect to DevOps topics. You are NOT a general assistant.' }}
8
+ {%- endif %}
9
+ {{- "
10
+
11
+ # Tools
12
+
13
+ You may call one or more functions to assist with the user query.
14
+
15
+ You are provided with function signatures within <tools></tools> XML tags:
16
+ <tools>" }}
17
+ {%- for tool in tools %}
18
+ {{- "
19
+ " }}
20
+ {{- tool | tojson }}
21
+ {%- endfor %}
22
+ {{- "
23
+ </tools>
24
+
25
+ For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
26
+ <tool_call>
27
+ {"name": <function-name>, "arguments": <args-json-object>}
28
+ </tool_call><|im_end|>
29
+ " }}
30
+ {%- else %}
31
+ {%- if messages[0]['role'] == 'system' %}
32
+ {{- '<|im_start|>system
33
+ ' + messages[0]['content'] + '<|im_end|>
34
+ ' }}
35
+ {%- else %}
36
+ {{- '<|im_start|>system
37
+ You are a specialized DevOps assistant. You ONLY help with DevOps-related topics like Kubernetes, Docker, CI/CD, infrastructure automation, monitoring, and cloud operations. If asked about non-DevOps topics (movies, weather, cooking, sports, music, travel, health, education, politics, religion, philosophy, entertainment, gaming, fashion, or any other non-DevOps topics), you MUST politely refuse and redirect to DevOps topics. You are NOT a general assistant.<|im_end|>
38
+ ' }}
39
+ {%- endif %}
40
+ {%- endif %}
41
+ {%- for message in messages %}
42
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
43
+ {{- '<|im_start|>' + message.role + '
44
+ ' + message.content + '<|im_end|>' + '
45
+ ' }}
46
+ {%- elif message.role == "assistant" %}
47
+ {{- '<|im_start|>' + message.role }}
48
+ {%- if message.content %}
49
+ {{- '
50
+ ' + message.content }}
51
+ {%- endif %}
52
+ {%- for tool_call in message.tool_calls %}
53
+ {%- if tool_call.function is defined %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '
57
+ <tool_call>
58
+ {"name": "' }}
59
+ {{- tool_call.name }}
60
+ {{- '", "arguments": ' }}
61
+ {{- tool_call.arguments | tojson }}
62
+ {{- '}
63
+ </tool_call>' }}
64
+ {%- endfor %}
65
+ {{- '<|im_end|>
66
+ ' }}
67
+ {%- elif message.role == "tool" %}
68
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
69
+ {{- '<|im_start|>user' }}
70
+ {%- endif %}
71
+ {{- '
72
+ <tool_response>
73
+ ' }}
74
+ {{- message.content }}
75
+ {{- '
76
+ </tool_response>' }}
77
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
78
+ {{- '<|im_end|>
79
+ ' }}
80
+ {%- endif %}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {%- if add_generation_prompt %}
84
+ {{- '<|im_start|>assistant
85
+ ' }}
86
+ {%- endif %}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0180d9179612e308a799d915cf8ccbcced4a006b9562e78fa1121cc61cc1b5
3
+ size 11422162
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|im_start|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<|im_start|>",
32
+ "<|im_end|>",
33
+ "<|endoftext|>"
34
+ ],
35
+ "bos_token": "<|im_start|>",
36
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\\nYou are a specialized DevOps assistant. You help with DevOps tasks only.<|im_end|>\\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "<|im_end|>",
39
+ "errors": "replace",
40
+ "model_max_length": 32768,
41
+ "pad_token": "<|endoftext|>",
42
+ "sp_model_kwargs": {},
43
+ "tokenizer_class": "PreTrainedTokenizerFast",
44
+ "unk_token": "<|endoftext|>",
45
+ "use_fast": true,
46
+ "vocab_size": 151646
47
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff