talha970/function-gemma-new
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: talha970/function-gemma-new
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-31 00:34:26 +08:00
commit 1951b0e4a3
18 changed files with 1647 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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

58
README.md Normal file
View File

@@ -0,0 +1,58 @@
---
base_model: google/functiongemma-270m-it
library_name: transformers
model_name: function-gemma-new
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for function-gemma-new
This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="talha970/function-gemma-new", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 1.3.0
- Transformers: 5.0.0
- Pytorch: 2.10.0+cu128
- Datasets: 4.8.5
- Tokenizers: 0.22.2
## Citations
Cite TRL as:
```bibtex
@software{vonwerra2020trl,
title = {{TRL: Transformers Reinforcement Learning}},
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
license = {Apache-2.0},
url = {https://github.com/huggingface/trl},
year = {2020}
}
```

279
chat_template.jinja Normal file
View 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
View 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": "5.0.0",
"use_bidirectional_attention": false,
"use_cache": false,
"vocab_size": 262144
}

15
generation_config.json Normal file
View 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": "5.0.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea12d58a23a97ae2ec01058ac8fc10afcb4a0ffa81e2391f1c63658c17b22c83
size 536223056

3
runs/May06_14-58-55_909defcf03f7/events.out.tfevents.1778079535.909defcf03f7.804.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98320d28b27421c3ea1098b45c3db4dc7bfd6d24bf526c76ec7fbed61ee19c5c
size 300736

3
runs/May06_15-32-55_909defcf03f7/events.out.tfevents.1778081575.909defcf03f7.804.1 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c244ebb16183150a26a5500407393e88b556967a04b49fccbbdae10302567122
size 496309

3
runs/May06_15-57-20_909defcf03f7/events.out.tfevents.1778083040.909defcf03f7.804.2 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7a185850d05f8a5fb60d904c5e7c6bf4b840e578c78ebd968cb2722d1f3946fb
size 116203

3
runs/May06_16-44-25_909defcf03f7/events.out.tfevents.1778085865.909defcf03f7.804.3 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:77190913999ce72c3495832b214f1413f4cc792e1659bfd34bcd8b883d4be5df
size 27065

3
runs/May06_17-00-31_909defcf03f7/events.out.tfevents.1778086831.909defcf03f7.804.4 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e7302532082dcbd6abeaa7df264ae9132959378f23e49499b62a66e99f0782d5
size 27064

3
runs/May06_17-11-38_909defcf03f7/events.out.tfevents.1778087498.909defcf03f7.804.5 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b913674dae71c2e0d665fe4ea4747e1664ba59d1d7b9524475737b4690000ea8
size 116203

3
runs/May06_17-28-57_909defcf03f7/events.out.tfevents.1778088537.909defcf03f7.804.6 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f55497f4af2d6ac160f280ed043a6cfd57229f907b108b62a62878801b653835
size 102592

3
runs/May06_17-36-25_fd102fa70b39/events.out.tfevents.1778088985.fd102fa70b39.488.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98b0c246ce73e2418d79ca036042949fc79b99686da9246105006802e02d09c6
size 496310

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e3655797f9d732b7dc08b4225200697af8e37d94b74711d9b1d8166feb953578
size 33384774

26
tokenizer_config.json Normal file
View 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": 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
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4fe8e361cab274d8dd5b1706ef40dca886bd731f07196c2c9a156202d8d5e8e5
size 5649

1138
training_data_manual_curated.csv Normal file
View File

File diff suppressed because it is too large Load Diff