初始化项目，由ModelHub XC社区提供模型
Model: beamcore/tools 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
|
||||
117
README.md
Normal file
117
README.md
Normal file
@@ -0,0 +1,117 @@
|
||||
---
|
||||
base_model: google/functiongemma-270m-it
|
||||
library_name: transformers
|
||||
model_name: beamcore/tools
|
||||
tags:
|
||||
- agent
|
||||
- tool-use
|
||||
- function-calling
|
||||
- on-device
|
||||
- beamcore
|
||||
- sft
|
||||
- trl
|
||||
license: gemma
|
||||
---
|
||||
|
||||
# 🛠️ beamcore/tools
|
||||
|
||||
This is a highly optimized, lightweight (270M parameters) function-calling model fine-tuned on top of `google/functiongemma-270m-it`. It is specifically designed to run **on-device (locally)** as a pre-flight search and routing assistant for the Elixir-native [Beamcore agent harness](https://beamcore.dev).
|
||||
|
||||
## 🚀 Purpose & Workflow
|
||||
|
||||
In agentic software engineering workflows, sending large workspace structures, complete file contents, and extensive tool schemas to massive frontier models is slow, expensive, and leads to context pollution.
|
||||
|
||||
`beamcore/tools` solves this by running locally to perform **pre-flight search routing**:
|
||||
1. **Analyze Intent**: When a user issues a request, `beamcore/tools` determines whether search/traversal tools are needed to gather codebase context.
|
||||
2. **Execute Tools**: If context is missing, it emits structured tool calls (e.g., `glob`, `grep`, `tree`, `read`) to fetch local file structures or code.
|
||||
3. **Minimize Tokens**: If no tools are required (or after search tools run and collect the necessary files), the main reasoning model is invoked with a minimal, relevant context, drastically reducing token overhead and billing.
|
||||
|
||||
```mermaid
|
||||
graph TD
|
||||
User([User Request]) --> Helper[beamcore/tools (Local 270M)]
|
||||
Helper -->|Needs Context?| ToolCall{Tool Call?}
|
||||
ToolCall -->|Yes| Exec[Execute Local Tool]
|
||||
Exec --> Read[Read/Grep/Glob Result]
|
||||
Read --> Main[Main Beamcore Agent]
|
||||
ToolCall -->|No / Finished| Main
|
||||
```
|
||||
|
||||
## 🛠️ Supported Tools
|
||||
|
||||
The model is fine-tuned to work with the following four workspace-inspection tools:
|
||||
|
||||
### 1. `glob`
|
||||
Find workspace files matching a glob pattern relative to a path.
|
||||
- **Parameters**: `pattern` (string, required), `path` (string, optional), `all` (boolean, optional).
|
||||
- **Example**: `{"pattern": "**/*.ex"}`
|
||||
|
||||
### 2. `grep`
|
||||
Search workspace file contents by regex with optional includes.
|
||||
- **Parameters**: `pattern` (string, required), `path` (string, optional), `include` (string, optional), `all` (boolean, optional).
|
||||
- **Example**: `{"pattern": "defmodule", "include": "*.ex"}`
|
||||
|
||||
### 3. `tree`
|
||||
Show a compact workspace directory tree with sizes.
|
||||
- **Parameters**: `path` (string, optional).
|
||||
- **Example**: `{"path": "lib/"}`
|
||||
|
||||
### 4. `read`
|
||||
Read a workspace-relative file or directory with offset/limit parameters.
|
||||
- **Parameters**: `filePath` (string, required), `offset` (integer, optional), `limit` (integer, optional).
|
||||
- **Example**: `{"filePath": "lib/beamcore.ex", "limit": 100}`
|
||||
|
||||
---
|
||||
|
||||
## 💻 Quickstart (Inference)
|
||||
|
||||
You can run `beamcore/tools` locally using `transformers`:
|
||||
|
||||
```python
|
||||
import json
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
from transformers.utils import get_json_schema
|
||||
|
||||
# Define tool signatures (converted to JSON Schema)
|
||||
def glob(pattern: str, path: str = None, all: bool = False): pass
|
||||
def grep(pattern: str, path: str = None, include: str = None, all: bool = False): pass
|
||||
def tree(path: str = None): pass
|
||||
def read(filePath: str, offset: int = 1, limit: int = 200): pass
|
||||
|
||||
tools = [
|
||||
get_json_schema(glob),
|
||||
get_json_schema(grep),
|
||||
get_json_schema(tree),
|
||||
get_json_schema(read)
|
||||
]
|
||||
|
||||
# Load model and tokenizer
|
||||
model_id = "beamcore/tools"
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
|
||||
# System prompt
|
||||
system_msg = "You are a pre-flight search assistant for a coding agent. Your ONLY job is to analyze the user request and determine if search or directory traversal tools are needed to find relevant code or files before the main coding agent answers."
|
||||
|
||||
messages = [
|
||||
{"role": "developer", "content": system_msg},
|
||||
{"role": "user", "content": "Find all Elixir source files in the project lib/ directory"}
|
||||
]
|
||||
|
||||
# Format chat using tools
|
||||
inputs = tokenizer.apply_chat_template(messages, tools=tools, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(inputs, max_new_tokens=256)
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## 📈 Training Details
|
||||
|
||||
- **Base Model**: `google/functiongemma-270m-it`
|
||||
- **Training Method**: Supervised Fine-Tuning (SFT) using TRL
|
||||
- **Dataset**: Custom search routing examples representing diverse developer queries (directory tree traversal, pattern matching, file reads, and conversational non-search queries).
|
||||
|
||||
### Framework Versions
|
||||
- TRL: 1.5.1
|
||||
- Transformers: 5.10.2
|
||||
- Pytorch: 2.12.0
|
||||
- Datasets: 5.0.0
|
||||
- Tokenizers: 0.22.2
|
||||
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 -%}
|
||||
62
config.json
Normal file
62
config.json
Normal file
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"_sliding_window_pattern": 6,
|
||||
"architectures": [
|
||||
"Gemma3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"bos_token_id": 2,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 1,
|
||||
"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": "5.10.2",
|
||||
"use_bidirectional_attention": false,
|
||||
"use_cache": false,
|
||||
"vocab_size": 262144
|
||||
}
|
||||
15
generation_config.json
Normal file
15
generation_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
1,
|
||||
50,
|
||||
106
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.10.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0970a77b160df827b6785fae49a97f304622c8ff0d5f9cb2b9009f3f4b8d1b4d
|
||||
size 536223056
|
||||
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
|
||||
27
tokenizer_config.json
Normal file
27
tokenizer_config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"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": false,
|
||||
"local_files_only": false,
|
||||
"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": "left",
|
||||
"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