初始化项目，由ModelHub XC社区提供模型
Model: arpacorp/micro-f1-mask Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
154
README.md
Normal file
154
README.md
Normal file
@@ -0,0 +1,154 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- zero-latency
|
||||
- pii-scrubbing
|
||||
- pii
|
||||
- compliance
|
||||
- privacy
|
||||
- function-calling
|
||||
- arpa
|
||||
- micro-f1-mask
|
||||
- micro-series
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
base_model: google/gemma-3-270m-it
|
||||
datasets:
|
||||
- synthetic
|
||||
model-index:
|
||||
- name: micro-f1-mask
|
||||
results: []
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
# ARPA MICRO SERIES: F1 MASK
|
||||
|
||||
**Zero-Latency PII Scrubbing - 270M Parameter Middleware**
|
||||
|
||||
<a href="https://huggingface.co/google/gemma-3-270m-it"><img src="https://img.shields.io/badge/base-Gemma_3_270M-bae6fd?style=flat-square" alt="Base Model"></a>
|
||||
<a href="#binary-mapping--tokens"><img src="https://img.shields.io/badge/task-PII_Scrubbing-efcefa?style=flat-square" alt="Task"></a>
|
||||
<a href="#training-methodology"><img src="https://img.shields.io/badge/training-PEFT_LoRA-bbf7d0?style=flat-square" alt="Training"></a>
|
||||
<a href="https://www.apache.org/licenses/LICENSE-2.0.html"><img src="https://img.shields.io/badge/license-Apache_2.0-fde68a?style=flat-square" alt="License"></a>
|
||||
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
**ARPA Micro Series: F1 Mask** is a high-performance fine-tuned model built to provide real-time identification and tokenization of Personally Identifiable Information (PII) for secure cloud computing.
|
||||
|
||||
Developed by [ARPA Hellenic Logical Systems](https://arpacorp.net), it acts as a privacy firewall for incoming/outgoing LLM prompts.
|
||||
|
||||
**GitHub**: [arpahls/micro-f1-mask](https://github.com/arpahls/micro-f1-mask) — Full training pipeline, Redis vault, and infrastructure.
|
||||
|
||||
## Model Summary
|
||||
|
||||
F1 Mask is a specialized fine-tune of [Gemma 3 270M IT](https://huggingface.co/google/gemma-3-270m-it). It is trained exclusively to output structured `replace_pii` function calls, effectively mapping sensitive data to safe tokens before they reach cloud-based LLMs.
|
||||
|
||||
## Quick Start
|
||||
|
||||
### 1. Register with Ollama
|
||||
|
||||
```bash
|
||||
# Direct SafeTensors registration
|
||||
ollama create micro-f1-mask --from arpacorp/micro-f1-mask
|
||||
|
||||
# Run detection
|
||||
ollama run micro-f1-mask "John Doe called from 555-0123 about invoice GB29NWBK60161331926819."
|
||||
```
|
||||
|
||||
### 2. Python (Transformers)
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("arpacorp/micro-f1-mask")
|
||||
tokenizer = AutoTokenizer.from_pretrained("arpacorp/micro-f1-mask")
|
||||
|
||||
prompt = """<start_of_turn>user
|
||||
You are Micro F1 Mask. Extract PII and output the 'replace_pii' function call.
|
||||
Draft an email to Jane Smith at jane@example.com.<end_of_turn>
|
||||
<start_of_turn>model
|
||||
"""
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.0)
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## Binary Mapping & Tokens
|
||||
|
||||
The model uses a deterministic tokenization scheme:
|
||||
|
||||
| Category | Token |
|
||||
|----------|-------|
|
||||
| INDIVIDUAL | [INDIVIDUAL_N] |
|
||||
| FINANCIAL | [FINANCIAL_N] |
|
||||
| LOCATION | [LOCATION_N] |
|
||||
| CONTACT | [CONTACT_N] |
|
||||
| ACCESS | [ACCESS_N] |
|
||||
| CORP | [CORP_N] |
|
||||
|
||||
### Example Output
|
||||
|
||||
```json
|
||||
{
|
||||
"name": "replace_pii",
|
||||
"arguments": {
|
||||
"entities": [
|
||||
{"type": "INDIVIDUAL", "val": "Jane Smith", "id": "[INDIVIDUAL_1]"},
|
||||
{"type": "CONTACT", "val": "jane@example.com", "id": "[CONTACT_1]"}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Training Methodology
|
||||
|
||||
- **Dataset**: 1,000 synthetic samples generated via high-entropy LLM workflows.
|
||||
- **Method**: PEFT / LoRA (Rank 16, Alpha 32).
|
||||
- **Epochs**: 3.
|
||||
- **Accuracy**: 76.10% (token-level generation).
|
||||
- **Latency**: Sub-50ms (inference on RTX 2070).
|
||||
|
||||
## Production Optimization Roadmap
|
||||
|
||||
While this repository provides a fully functional 1,000-sample prototype, reaching 95%+ enterprise accuracy requires the following architectural optimizations:
|
||||
|
||||
### 1. Hard-Negative Mining (Re-training)
|
||||
To push accuracy into the high 90s, the model must iteratively learn from its mistakes:
|
||||
1. **Scale**: Use the synthetic generator to produce 10,000 - 50,000 highly diverse samples tailored to your industry.
|
||||
2. **Evaluate**: Run an evaluation script to benchmark against samples of your real-world traffic.
|
||||
3. **Mine Edge Cases**: Every time the model misses a PII token (a "hard negative"), extract that sentence structure, generate 500 synthetic variations of that specific edge-case, and re-run the fine-tuning pipeline.
|
||||
|
||||
### 2. Human-In-The-Loop (HITL) Workflows
|
||||
For mission-critical data, we recommend extending the middleware bridge to include human oversight:
|
||||
|
||||
- **Pre-Cloud Quarantine (Maximum Security):** Modify the endpoint so that when F1 Mask detects PII, the API payload pauses. The application UI highlights the detected entities to the user. The user manually verifies the masking *before* the payload is authorized to hit the external cloud.
|
||||
- **Post-Reconstruction Review (Quality Control):** Allow the fully automated process to finish. Before the final reconstructed cloud response is saved or emailed, route it to an analyst dashboard where a human can manually verify the grammar of the reconstructed payload.
|
||||
|
||||
## Enterprise Solutions
|
||||
|
||||
The public release of **ARPA F1 Mask** serves as a lightweight demonstration of how the *Function One (F1)* architecture can be fine-tuned for structured privacy enforcement.
|
||||
|
||||
For mission-critical infrastructure, ARPA offers an actively maintained, highly robust enterprise tier. Organizations can deploy our gated version out-of-the-box and completely offload the burden of continuous maintenance, bespoke fine-tuning, concept drift avoidance, and rigorous scenario evaluations.
|
||||
|
||||
For enterprise licensing or to discuss tailoring the F1 model to your proprietary data schemas, reach out to: **[input@arpacorp.net](mailto:input@arpacorp.net)**
|
||||
|
||||
## Ethical Considerations
|
||||
|
||||
**Data Provenance**: No real PII was used in the training of this model. All examples were synthetically generated to mimic enterprise communication patterns.
|
||||
|
||||
**Intended Use**: This model is designed for middleware. It is not intended to be used as a conversational assistant. It is a one-way security gate that focuses exclusively on privacy enforcement.
|
||||
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
<img src="https://raw.githubusercontent.com/ARPAHLS/skillware/main/assets/arpalogo.png" width="50px">
|
||||
|
||||
Built by [ARPA Hellenic Logical Systems](https://arpacorp.net)
|
||||
|
||||
</div>
|
||||
279
chat_template.jinja
Normal file
279
chat_template.jinja
Normal file
@@ -0,0 +1,279 @@
|
||||
{%- macro format_parameters(properties, required) -%}
|
||||
{%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
|
||||
{%- set ns = namespace(found_first=false) -%}
|
||||
{%- for key, value in properties | dictsort -%}
|
||||
{%- if key not in standard_keys -%}
|
||||
{%- if ns.found_first %},{% endif -%}
|
||||
{%- set ns.found_first = true -%}
|
||||
{{- key }}:{description:<escape>{{ value['description'] }}<escape>
|
||||
{%- if value['type'] | upper == 'STRING' -%}
|
||||
{%- if value['enum'] -%}
|
||||
,enum:{{ format_argument(value['enum']) }}
|
||||
{%- endif -%}
|
||||
{%- elif value['type'] | upper == 'OBJECT' -%}
|
||||
,properties:{
|
||||
{%- if value['properties'] is defined and value['properties'] is mapping -%}
|
||||
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
|
||||
{%- elif value is mapping -%}
|
||||
{{- format_parameters(value, value['required'] | default([])) -}}
|
||||
{%- endif -%}
|
||||
}
|
||||
{%- if value['required'] -%}
|
||||
,required:[
|
||||
{%- for item in value['required'] | default([]) -%}
|
||||
<escape>{{- item -}}<escape>
|
||||
{%- if not loop.last %},{% endif -%}
|
||||
{%- endfor -%}
|
||||
]
|
||||
{%- endif -%}
|
||||
{%- elif value['type'] | upper == 'ARRAY' -%}
|
||||
{%- if value['items'] is mapping and value['items'] -%}
|
||||
,items:{
|
||||
{%- set ns_items = namespace(found_first=false) -%}
|
||||
{%- for item_key, item_value in value['items'] | dictsort -%}
|
||||
{%- if item_value is not none -%}
|
||||
{%- if ns_items.found_first %},{% endif -%}
|
||||
{%- set ns_items.found_first = true -%}
|
||||
{%- if item_key == 'properties' -%}
|
||||
properties:{
|
||||
{%- if item_value is mapping -%}
|
||||
{{- format_parameters(item_value, value['items']['required'] | default([])) -}}
|
||||
{%- endif -%}
|
||||
}
|
||||
{%- elif item_key == 'required' -%}
|
||||
required:[
|
||||
{%- for req_item in item_value -%}
|
||||
<escape>{{- req_item -}}<escape>
|
||||
{%- if not loop.last %},{% endif -%}
|
||||
{%- endfor -%}
|
||||
]
|
||||
{%- elif item_key == 'type' -%}
|
||||
{%- if item_value is string -%}
|
||||
type:{{ format_argument(item_value | upper) }}
|
||||
{%- else -%}
|
||||
type:{{ format_argument(item_value | map('upper') | list) }}
|
||||
{%- endif -%}
|
||||
{%- else -%}
|
||||
{{ item_key }}:{{ format_argument(item_value) }}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
,type:<escape>{{ value['type'] | upper }}<escape>}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- endmacro -%}
|
||||
{% macro format_function_declaration(tool_data) -%}
|
||||
declaration:{{- tool_data['function']['name'] -}}
|
||||
{description:<escape>{{- tool_data['function']['description'] -}}<escape>
|
||||
{%- set params = tool_data['function']['parameters'] -%}
|
||||
{%- if params -%}
|
||||
,parameters:{
|
||||
{%- if params['properties'] -%}
|
||||
properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
|
||||
{%- endif -%}
|
||||
{%- if params['required'] -%}
|
||||
required:[
|
||||
{%- for item in params['required'] -%}
|
||||
<escape>{{- item -}}<escape>
|
||||
{{- ',' if not loop.last -}}
|
||||
{%- endfor -%}
|
||||
],
|
||||
{%- endif -%}
|
||||
{%- if params['type'] -%}
|
||||
type:<escape>{{- params['type'] | upper -}}<escape>}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
}
|
||||
{%- endmacro -%}
|
||||
{% macro format_argument(argument, escape_keys=True) -%}
|
||||
{%- if argument is string -%}
|
||||
{{- '<escape>' + argument + '<escape>' -}}
|
||||
{%- elif argument is boolean -%}
|
||||
{%- if argument -%}
|
||||
{{- 'true' -}}
|
||||
{%- else -%}
|
||||
{{- 'false' -}}
|
||||
{%- endif -%}
|
||||
{%- elif argument is mapping -%}
|
||||
{{- '{' -}}
|
||||
{%- set ns = namespace(found_first=false) -%}
|
||||
{%- for key, value in argument | dictsort -%}
|
||||
{%- if ns.found_first %},{% endif -%}
|
||||
{%- set ns.found_first = true -%}
|
||||
{%- if escape_keys -%}
|
||||
{{- '<escape>' + key + '<escape>' -}}
|
||||
{%- else -%}
|
||||
{{- key -}}
|
||||
{%- endif -%}
|
||||
:{{- format_argument(value, escape_keys=escape_keys) -}}
|
||||
{%- endfor -%}
|
||||
{{- '}' -}}
|
||||
{%- elif argument is sequence -%}
|
||||
{{- '[' -}}
|
||||
{%- for item in argument -%}
|
||||
{{- format_argument(item, escape_keys=escape_keys) -}}
|
||||
{%- if not loop.last %},{% endif -%}
|
||||
{%- endfor -%}
|
||||
{{- ']' -}}
|
||||
{%- else -%}
|
||||
{{- argument -}}
|
||||
{%- endif -%}
|
||||
{%- endmacro -%}
|
||||
{{ bos_token }}
|
||||
{%- set ns = namespace(prev_message_type=None) -%}
|
||||
{#- Tool Declarations -#}
|
||||
{%- set loop_messages = messages -%}
|
||||
{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
|
||||
{{- '<start_of_turn>developer\n' -}}
|
||||
{%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
|
||||
{%- if messages[0]['content'] is string -%}
|
||||
{{- messages[0]['content'] | trim -}}
|
||||
{%- elif messages[0]['content'] is sequence -%}
|
||||
{%- for item in messages[0]['content'] -%}
|
||||
{%- if item['type'] == 'text' -%}
|
||||
{{- item['text'] | trim -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- endif -%}
|
||||
{%- set loop_messages = messages[1:] -%}
|
||||
{%- endif -%}
|
||||
{%- if tools -%}
|
||||
{%- for tool in tools %}
|
||||
{{- '<start_function_declaration>' -}}
|
||||
{{- format_function_declaration(tool) | trim }}
|
||||
{{- '<end_function_declaration>' -}}
|
||||
{%- endfor %}
|
||||
{%- endif -%}
|
||||
{{- '<end_of_turn>\n' }}
|
||||
{%- endif %}
|
||||
{#- Loop through messages. -#}
|
||||
{%- for message in loop_messages -%}
|
||||
{%- if (message['role'] == 'assistant') -%}
|
||||
{#- Rename "assistant" to "model". -#}
|
||||
{%- set role = "model" -%}
|
||||
{%- else -%}
|
||||
{%- set role = message['role'] -%}
|
||||
{%- endif -%}
|
||||
{%- if role != 'tool' -%}
|
||||
{%- if ns.prev_message_type != 'tool_response' -%}
|
||||
{{- '<start_of_turn>' + role + '\n' }}
|
||||
{%- endif -%}
|
||||
{%- set ns.prev_message_type = None -%}
|
||||
{%- if 'content' in message and message['content'] is not none -%}
|
||||
{%- if message['content'] is string -%}
|
||||
{{ message['content'] | trim }}
|
||||
{%- elif message['content'] is sequence -%}
|
||||
{%- for item in message['content'] -%}
|
||||
{%- if item['type'] == 'image' -%}
|
||||
{{ '<start_of_image>' }}
|
||||
{%- elif item['type'] == 'text' -%}
|
||||
{{ item['text'] | trim }}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid content type in user/assistant message") }}
|
||||
{%- endif -%}
|
||||
{%- set ns.prev_message_type = 'content' -%}
|
||||
{%- endif -%}
|
||||
{%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
|
||||
{#- Tool Calls -#}
|
||||
{%- for tool_call in message['tool_calls'] -%}
|
||||
{% set function = tool_call['function'] %}
|
||||
{{- '<start_function_call>call:' + function['name'] + '{' -}}
|
||||
{%- if 'arguments' in function -%}
|
||||
{%- if function['arguments'] is mapping -%}
|
||||
{%- set ns = namespace(found_first=false) -%}
|
||||
{%- for key, value in function['arguments'] | dictsort -%}
|
||||
{%- if ns.found_first %},{% endif -%}
|
||||
{%- set ns.found_first = true -%}
|
||||
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
||||
{%- endfor -%}
|
||||
{%- elif function['arguments'] is string -%}
|
||||
{# This handles string-JSON, just in case #}
|
||||
{{ function['arguments'] }}
|
||||
{%- endif %}
|
||||
{%- endif -%}
|
||||
{{- '}<end_function_call>' -}}
|
||||
{%- endfor -%}
|
||||
{%- if loop.last -%}
|
||||
{{ '<start_function_response>' }}
|
||||
{%- endif -%}
|
||||
{%- set ns.prev_message_type = 'tool_call' -%}
|
||||
{%- endif -%}
|
||||
{%- else -%}
|
||||
{#- Tool Responses -#}
|
||||
{%- if 'content' in message and message['content'] -%}
|
||||
{%- if message['content'] is mapping -%}
|
||||
{%- if 'name' in message['content'] and 'response' in message['content'] -%}
|
||||
{{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
|
||||
{%- set response_ns = namespace(found_first=false) -%}
|
||||
{%- for key, value in message['content']['response'] | dictsort -%}
|
||||
{%- if response_ns.found_first %},{% endif -%}
|
||||
{%- set response_ns.found_first = true -%}
|
||||
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
||||
{%- endfor -%}
|
||||
{{- '}<end_function_response>' -}}
|
||||
{%- elif 'name' in message -%}
|
||||
{{ '<start_function_response>response:' + message['name'] | trim + '{' }}
|
||||
{%- set response_ns = namespace(found_first=false) -%}
|
||||
{%- for key, value in message['content'] | dictsort -%}
|
||||
{%- if response_ns.found_first %},{% endif -%}
|
||||
{%- set response_ns.found_first = true -%}
|
||||
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
||||
{%- endfor -%}
|
||||
{{- '}<end_function_response>' -}}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
|
||||
{%- endif -%}
|
||||
{%- elif message['content'] is string -%}
|
||||
{%- if 'name' in message -%}
|
||||
{{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid tool response: 'name' must be provided.") }}
|
||||
{%- endif -%}
|
||||
{%- elif message['content'] is sequence -%}
|
||||
{%- for item in message['content'] -%}
|
||||
{%- if item is mapping -%}
|
||||
{%- if 'name' in item and 'response' in item -%}
|
||||
{{ '<start_function_response>response:' + item['name'] | trim + '{' }}
|
||||
{%- set response_ns = namespace(found_first=false) -%}
|
||||
{%- for key, value in item['response'] | dictsort -%}
|
||||
{%- if response_ns.found_first %},{% endif -%}
|
||||
{%- set response_ns.found_first = true -%}
|
||||
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
||||
{%- endfor -%}
|
||||
{{- '}<end_function_response>' -}}
|
||||
{%- elif 'name' in message -%}
|
||||
{{ '<start_function_response>response:' + message['name'] | trim + '{' }}
|
||||
{%- set response_ns = namespace(found_first=false) -%}
|
||||
{%- for key, value in item | dictsort -%}
|
||||
{%- if response_ns.found_first %},{% endif -%}
|
||||
{%- set response_ns.found_first = true -%}
|
||||
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
||||
{%- endfor -%}
|
||||
{{- '}<end_function_response>' -}}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
|
||||
{%- endif -%}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- set ns.prev_message_type = 'tool_response' -%}
|
||||
{%- endif -%}
|
||||
{%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
|
||||
{{ '<end_of_turn>\n' }}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{%- if ns.prev_message_type != 'tool_response' -%}
|
||||
{{- '<start_of_turn>model\n' -}}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
65
config.json
Normal file
65
config.json
Normal file
@@ -0,0 +1,65 @@
|
||||
{
|
||||
"_sliding_window_pattern": 6,
|
||||
"architectures": [
|
||||
"Gemma3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"bos_token_id": 2,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": [
|
||||
1,
|
||||
50
|
||||
],
|
||||
"final_logit_softcapping": null,
|
||||
"head_dim": 256,
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"hidden_size": 640,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2048,
|
||||
"layer_types": [
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "gemma3_text",
|
||||
"num_attention_heads": 4,
|
||||
"num_hidden_layers": 18,
|
||||
"num_key_value_heads": 1,
|
||||
"pad_token_id": 0,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"full_attention": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_attention": {
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default"
|
||||
}
|
||||
},
|
||||
"sliding_window": 512,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_bidirectional_attention": false,
|
||||
"use_cache": true,
|
||||
"vocab_size": 262144
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
50,
|
||||
106
|
||||
],
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:81749bec1fbbb9915dcf519c447c8015f6fb17a521c97bcc07f261021479cbf8
|
||||
size 536222816
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
|
||||
size 33384898
|
||||
26
tokenizer_config.json
Normal file
26
tokenizer_config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"boi_token": "<start_of_image>",
|
||||
"bos_token": "<bos>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eoi_token": "<end_of_image>",
|
||||
"eos_token": "<eos>",
|
||||
"image_token": "<image_soft_token>",
|
||||
"is_local": true,
|
||||
"mask_token": "<mask>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"model_specific_special_tokens": {
|
||||
"boi_token": "<start_of_image>",
|
||||
"eoi_token": "<end_of_image>",
|
||||
"image_token": "<image_soft_token>",
|
||||
"sfr_token": "<start_function_response>"
|
||||
},
|
||||
"pad_token": "<pad>",
|
||||
"padding_side": "right",
|
||||
"sfr_token": "<start_function_response>",
|
||||
"sp_model_kwargs": null,
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "GemmaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user