初始化项目，由ModelHub XC社区提供模型
Model: kenny2021/episodic-simpo-v4.3-merged 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
|
||||
21
README.md
Normal file
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
||||
---
|
||||
base_model: kenny2021/episodic-lora-merged
|
||||
tags:
|
||||
- text-generation-inference
|
||||
- transformers
|
||||
- unsloth
|
||||
- gemma3_text
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# Uploaded finetuned model
|
||||
|
||||
- **Developed by:** kenny2021
|
||||
- **License:** apache-2.0
|
||||
- **Finetuned from model :** kenny2021/episodic-lora-merged
|
||||
|
||||
This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<end_of_image>": 262145,
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
282
chat_template.jinja
Normal file
282
chat_template.jinja
Normal file
@@ -0,0 +1,282 @@
|
||||
{%- 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:] -%}
|
||||
{%- else -%}
|
||||
{{- 'You are a model that can do function calling with the following functions' -}}
|
||||
{%- set loop_messages = messages -%}
|
||||
{%- 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 -%}
|
||||
57
config.json
Normal file
57
config.json
Normal file
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"_sliding_window_pattern": 6,
|
||||
"architectures": [
|
||||
"Gemma3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"bos_token_id": 2,
|
||||
"torch_dtype": "bfloat16",
|
||||
"eos_token_id": 106,
|
||||
"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_name": "unsloth/functiongemma-270m-it-unsloth-bnb-4bit",
|
||||
"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_local_base_freq": 10000.0,
|
||||
"rope_parameters": null,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 512,
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.4.6",
|
||||
"use_bidirectional_attention": false,
|
||||
"use_cache": true,
|
||||
"vocab_size": 262144
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac64a4ce3893aa6d815a1145b1407b349c0567593ea12f292e0331b5411604fe
|
||||
size 536223056
|
||||
34
special_tokens_map.json
Normal file
34
special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"boi_token": "<start_of_image>",
|
||||
"bos_token": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eoi_token": "<end_of_image>",
|
||||
"eos_token": {
|
||||
"content": "<end_of_turn>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"image_token": "<image_soft_token>",
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sfr_token": "<start_function_response>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
|
||||
size 33384899
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aa009fcbc3589a9904d30d04834094fea4653c2ac6d2de2cd1262d4f7a50ceb3
|
||||
size 4689144
|
||||
51356
tokenizer_config.json
Normal file
51356
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user