Xunzhuo commited on
Commit
0bd6a80
·
verified ·
1 Parent(s): e503e8d

Update Hugging Face org references: llm-semantic-router → vllm-sr

Browse files
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: llm-semantic-router/mmbert-32k-yarn
3
  library_name: peft
4
  license: apache-2.0
5
  language:
@@ -18,7 +18,7 @@ tags:
18
  - mmbert
19
  - 32k-context
20
  datasets:
21
- - llm-semantic-router/feedback-detector-dataset
22
  metrics:
23
  - accuracy
24
  - f1
@@ -31,7 +31,7 @@ model-index:
31
  name: User Feedback Classification
32
  dataset:
33
  name: feedback-detector-dataset
34
- type: llm-semantic-router/feedback-detector-dataset
35
  metrics:
36
  - name: Accuracy
37
  type: accuracy
@@ -43,7 +43,7 @@ model-index:
43
 
44
  # mmBERT-32K Feedback Detector (LoRA)
45
 
46
- A 4-class user feedback classifier fine-tuned from [mmbert-32k-yarn](https://huggingface.co/llm-semantic-router/mmbert-32k-yarn) using LoRA (Low-Rank Adaptation).
47
 
48
  ## Model Description
49
 
@@ -85,13 +85,13 @@ from peft import PeftModel
85
 
86
  # Load base model
87
  base_model = AutoModelForSequenceClassification.from_pretrained(
88
- "llm-semantic-router/mmbert-32k-yarn",
89
  num_labels=4
90
  )
91
- tokenizer = AutoTokenizer.from_pretrained("llm-semantic-router/mmbert-32k-yarn")
92
 
93
  # Load LoRA adapter
94
- model = PeftModel.from_pretrained(base_model, "llm-semantic-router/mmbert32k-feedback-detector-lora")
95
  model.eval()
96
 
97
  # Inference
@@ -112,10 +112,10 @@ For easier deployment, use the merged version:
112
  from transformers import AutoModelForSequenceClassification, AutoTokenizer
113
 
114
  model = AutoModelForSequenceClassification.from_pretrained(
115
- "llm-semantic-router/mmbert32k-feedback-detector-merged"
116
  )
117
  tokenizer = AutoTokenizer.from_pretrained(
118
- "llm-semantic-router/mmbert32k-feedback-detector-merged"
119
  )
120
  ```
121
 
@@ -125,7 +125,7 @@ tokenizer = AutoTokenizer.from_pretrained(
125
 
126
  | Parameter | Value |
127
  |-----------|-------|
128
- | Base Model | llm-semantic-router/mmbert-32k-yarn |
129
  | LoRA Rank | 64 |
130
  | LoRA Alpha | 128 |
131
  | LoRA Dropout | 0.1 |
@@ -140,7 +140,7 @@ tokenizer = AutoTokenizer.from_pretrained(
140
 
141
  ### Training Data
142
 
143
- Trained on [llm-semantic-router/feedback-detector-dataset](https://huggingface.co/datasets/llm-semantic-router/feedback-detector-dataset):
144
  - **Training samples**: 17,896 (balanced across 4 classes)
145
  - **Validation samples**: 2,985
146
 
@@ -172,7 +172,7 @@ The model inherits multilingual capabilities from mmbert-32k-yarn (Glot500 token
172
  author={LLM Semantic Router Team},
173
  year={2026},
174
  publisher={Hugging Face},
175
- url={https://huggingface.co/llm-semantic-router/mmbert32k-feedback-detector-lora}
176
  }
177
  ```
178
 
 
1
  ---
2
+ base_model: vllm-sr/mmbert-32k-yarn
3
  library_name: peft
4
  license: apache-2.0
5
  language:
 
18
  - mmbert
19
  - 32k-context
20
  datasets:
21
+ - vllm-sr/feedback-detector-dataset
22
  metrics:
23
  - accuracy
24
  - f1
 
31
  name: User Feedback Classification
32
  dataset:
33
  name: feedback-detector-dataset
34
+ type: vllm-sr/feedback-detector-dataset
35
  metrics:
36
  - name: Accuracy
37
  type: accuracy
 
43
 
44
  # mmBERT-32K Feedback Detector (LoRA)
45
 
46
+ A 4-class user feedback classifier fine-tuned from [mmbert-32k-yarn](https://huggingface.co/vllm-sr/mmbert-32k-yarn) using LoRA (Low-Rank Adaptation).
47
 
48
  ## Model Description
49
 
 
85
 
86
  # Load base model
87
  base_model = AutoModelForSequenceClassification.from_pretrained(
88
+ "vllm-sr/mmbert-32k-yarn",
89
  num_labels=4
90
  )
91
+ tokenizer = AutoTokenizer.from_pretrained("vllm-sr/mmbert-32k-yarn")
92
 
93
  # Load LoRA adapter
94
+ model = PeftModel.from_pretrained(base_model, "vllm-sr/mmbert32k-feedback-detector-lora")
95
  model.eval()
96
 
97
  # Inference
 
112
  from transformers import AutoModelForSequenceClassification, AutoTokenizer
113
 
114
  model = AutoModelForSequenceClassification.from_pretrained(
115
+ "vllm-sr/mmbert32k-feedback-detector-merged"
116
  )
117
  tokenizer = AutoTokenizer.from_pretrained(
118
+ "vllm-sr/mmbert32k-feedback-detector-merged"
119
  )
120
  ```
121
 
 
125
 
126
  | Parameter | Value |
127
  |-----------|-------|
128
+ | Base Model | vllm-sr/mmbert-32k-yarn |
129
  | LoRA Rank | 64 |
130
  | LoRA Alpha | 128 |
131
  | LoRA Dropout | 0.1 |
 
140
 
141
  ### Training Data
142
 
143
+ Trained on [vllm-sr/feedback-detector-dataset](https://huggingface.co/datasets/vllm-sr/feedback-detector-dataset):
144
  - **Training samples**: 17,896 (balanced across 4 classes)
145
  - **Validation samples**: 2,985
146
 
 
172
  author={LLM Semantic Router Team},
173
  year={2026},
174
  publisher={Hugging Face},
175
+ url={https://huggingface.co/vllm-sr/mmbert32k-feedback-detector-lora}
176
  }
177
  ```
178
 
adapter_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
- "base_model_name_or_path": "llm-semantic-router/mmbert-32k-yarn",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
 
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
+ "base_model_name_or_path": "vllm-sr/mmbert-32k-yarn",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
checkpoint-4500/README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- base_model: llm-semantic-router/mmbert-32k-yarn
3
  library_name: peft
4
  tags:
5
- - base_model:adapter:llm-semantic-router/mmbert-32k-yarn
6
  - lora
7
  - transformers
8
  ---
 
1
  ---
2
+ base_model: vllm-sr/mmbert-32k-yarn
3
  library_name: peft
4
  tags:
5
+ - base_model:adapter:vllm-sr/mmbert-32k-yarn
6
  - lora
7
  - transformers
8
  ---
checkpoint-4500/adapter_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
- "base_model_name_or_path": "llm-semantic-router/mmbert-32k-yarn",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
 
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
+ "base_model_name_or_path": "vllm-sr/mmbert-32k-yarn",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
checkpoint-6000/README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- base_model: llm-semantic-router/mmbert-32k-yarn
3
  library_name: peft
4
  tags:
5
- - base_model:adapter:llm-semantic-router/mmbert-32k-yarn
6
  - lora
7
  - transformers
8
  ---
 
1
  ---
2
+ base_model: vllm-sr/mmbert-32k-yarn
3
  library_name: peft
4
  tags:
5
+ - base_model:adapter:vllm-sr/mmbert-32k-yarn
6
  - lora
7
  - transformers
8
  ---
checkpoint-6000/adapter_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
- "base_model_name_or_path": "llm-semantic-router/mmbert-32k-yarn",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
 
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
+ "base_model_name_or_path": "vllm-sr/mmbert-32k-yarn",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
training_config.json CHANGED
@@ -18,7 +18,7 @@
18
  "2": "WRONG_ANSWER",
19
  "3": "WANT_DIFFERENT"
20
  },
21
- "base_model": "llm-semantic-router/mmbert-32k-yarn",
22
  "max_length": 512,
23
  "use_lora": true,
24
  "lora_rank": 64,
 
18
  "2": "WRONG_ANSWER",
19
  "3": "WANT_DIFFERENT"
20
  },
21
+ "base_model": "vllm-sr/mmbert-32k-yarn",
22
  "max_length": 512,
23
  "use_lora": true,
24
  "lora_rank": 64,