初始化项目，由ModelHub XC社区提供模型
Model: Xkev/gemma-3-1b-it-kk 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
|
||||
38
README.md
Normal file
38
README.md
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
license: mit
|
||||
datasets:
|
||||
- K-and-K/knights-and-knaves
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- google/gemma-3-1b-it
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- knights-and-knaves
|
||||
- gemma3
|
||||
---
|
||||
|
||||
|
||||
# Gemma-3-1B-IT — Knights-and-Knaves SFT
|
||||
|
||||
Paper Link: [https://arxiv.org/abs/2605.28814](https://arxiv.org/abs/2605.28814)
|
||||
|
||||
Cold-start supervised-fine-tuned (SFT) model of [`google/gemma-3-1b-it`](https://huggingface.co/google/gemma-3-1b-it) on the [Knights-and-Knaves](https://huggingface.co/datasets/K-and-K/knights-and-knaves) (K&K) logic-puzzle dataset.
|
||||
|
||||
For the post-trained model on top of this SFT model, see [`Xkev/gemma-3-1b-it-kk-bes`](https://huggingface.co/Xkev/gemma-3-1b-it-kk-bes).
|
||||
|
||||
## Training
|
||||
|
||||
- **Base model**: `google/gemma-3-1b-it`
|
||||
- **Dataset**: K&K puzzles (1k subset), formatted as chat with reasoning + JSON answer
|
||||
- **Framework**: [verl](https://github.com/volcengine/verl) `sft_trainer`
|
||||
- **Hyperparameters**: `lr=1e-5`, `weight_decay=0.01`, `lr_warmup_ratio=0.1`, cosine schedule, `epochs=3`, `dtype=bf16`
|
||||
|
||||
## Intended use
|
||||
|
||||
Research on logical reasoning and post-training. Not intended for general dialog or production.
|
||||
|
||||
## License
|
||||
|
||||
MIT. Base model `google/gemma-3-1b-it` is governed by Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms), which still apply to this model.
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
45
chat_template.jinja
Normal file
45
chat_template.jinja
Normal file
@@ -0,0 +1,45 @@
|
||||
{{ bos_token }}
|
||||
{%- if messages[0]['role'] == 'system' -%}
|
||||
{%- if messages[0]['content'] is string -%}
|
||||
{%- set first_user_prefix = messages[0]['content'] + '
|
||||
|
||||
' -%}
|
||||
{%- else -%}
|
||||
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
||||
|
||||
' -%}
|
||||
{%- endif -%}
|
||||
{%- set loop_messages = messages[1:] -%}
|
||||
{%- else -%}
|
||||
{%- set first_user_prefix = "" -%}
|
||||
{%- set loop_messages = messages -%}
|
||||
{%- endif -%}
|
||||
{%- for message in loop_messages -%}
|
||||
|
||||
{%- if (message['role'] == 'assistant') -%}
|
||||
{%- set role = "model" -%}
|
||||
{%- else -%}
|
||||
{%- set role = message['role'] -%}
|
||||
{%- endif -%}
|
||||
{{ '<start_of_turn>' + role + '
|
||||
' + (first_user_prefix if loop.first else "") }}
|
||||
{%- if message['content'] is string -%}
|
||||
{{ message['content'] | trim }}
|
||||
{%- elif message['content'] is iterable -%}
|
||||
{%- 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") }}
|
||||
{%- endif -%}
|
||||
{{ '<end_of_turn>
|
||||
' }}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{'<start_of_turn>model
|
||||
'}}
|
||||
{%- endif -%}
|
||||
64
config.json
Normal file
64
config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"_sliding_window_pattern": 6,
|
||||
"architectures": [
|
||||
"Gemma3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 1,
|
||||
"final_logit_softcapping": null,
|
||||
"head_dim": 256,
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1152,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6912,
|
||||
"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",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "gemma3_text",
|
||||
"num_attention_heads": 4,
|
||||
"num_hidden_layers": 26,
|
||||
"num_key_value_heads": 1,
|
||||
"pad_token_id": 0,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_local_base_freq": 10000,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": 512,
|
||||
"sliding_window_pattern": 6,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_bidirectional_attention": false,
|
||||
"use_cache": true,
|
||||
"vocab_size": 262144
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1705ee3d412386376521e02162ab5fadf771ccffb41fefccb6873b54aaba0c2a
|
||||
size 2603791264
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"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": "<eos>",
|
||||
"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
|
||||
},
|
||||
"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 sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
||||
size 33384568
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
||||
size 4689074
|
||||
51345
tokenizer_config.json
Normal file
51345
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user