初始化项目，由ModelHub XC社区提供模型
Model: Paulwalker4884/gemma-3-1b-terminal-assistant 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
|
||||
168
README.md
Normal file
168
README.md
Normal file
@@ -0,0 +1,168 @@
|
||||
---
|
||||
license: gemma
|
||||
base_model:
|
||||
- google/gemma-3-1b-it
|
||||
tags:
|
||||
- gemma
|
||||
- terminal
|
||||
- linux
|
||||
- command-generation
|
||||
- sft
|
||||
- Mica
|
||||
- fine-tuned
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# Gemma 3 1B Terminal Assistant
|
||||
|
||||
A fine-tuned version of Google's **Gemma 3 1B Instruction Tuned model** specialized for terminal command generation.
|
||||
|
||||
This model was trained to understand natural language requests and generate safe, minimal terminal commands.
|
||||
|
||||
## Model Details
|
||||
|
||||
Base Model:
|
||||
|
||||
- google/gemma-3-1b-it
|
||||
|
||||
Fine-tuning Method:
|
||||
|
||||
- Supervised Fine-Tuning (SFT)
|
||||
- Mica fine-tuning
|
||||
- Mica merged into the base model
|
||||
|
||||
Training Dataset:
|
||||
|
||||
- mshojaei77/terminal-command-execution-sft
|
||||
|
||||
Task:
|
||||
|
||||
- Linux terminal commands
|
||||
- Windows commands
|
||||
- Shell scripting
|
||||
- Command explanation
|
||||
- Safe command generation
|
||||
|
||||
|
||||
## Example Usage
|
||||
|
||||
|
||||
### Python Example
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
|
||||
model_name = "Paulwalker4884/gemma-3-1b-terminal-assistant"
|
||||
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a safe terminal command assistant."
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Find all python files recursively"
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
).to(model.device)
|
||||
|
||||
|
||||
outputs = model.generate(
|
||||
inputs,
|
||||
max_new_tokens=128,
|
||||
temperature=0.2
|
||||
)
|
||||
|
||||
|
||||
response = tokenizer.decode(
|
||||
outputs[0][inputs.shape[-1]:],
|
||||
skip_special_tokens=True
|
||||
)
|
||||
|
||||
|
||||
print(response)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Example
|
||||
|
||||
Input:
|
||||
|
||||
```
|
||||
Find all python files recursively
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```bash
|
||||
find . -name "*.py"
|
||||
```
|
||||
|
||||
|
||||
Input:
|
||||
|
||||
```
|
||||
Find all log files modified in the last 7 days and save them
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```bash
|
||||
find . -name "*.log" -mtime -7 > recent_logs.txt
|
||||
```
|
||||
|
||||
|
||||
## Safety
|
||||
|
||||
This model is trained to avoid blindly generating destructive commands.
|
||||
|
||||
For potentially dangerous operations, users should verify commands before execution.
|
||||
|
||||
|
||||
## Limitations
|
||||
|
||||
- The model may generate incorrect commands.
|
||||
- Always review generated commands before running them.
|
||||
- Performance depends on the quality of the input prompt.
|
||||
|
||||
|
||||
## Training Information
|
||||
|
||||
Dataset size:
|
||||
|
||||
- Train: 31,429 examples
|
||||
- Evaluation: 239 examples
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Frameworks:
|
||||
|
||||
- Transformers
|
||||
- TRL
|
||||
- PEFT
|
||||
- PyTorch
|
||||
|
||||
BY : Yasin Keykha
|
||||
47
chat_template.jinja
Normal file
47
chat_template.jinja
Normal file
@@ -0,0 +1,47 @@
|
||||
{{ 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'] == 'user') != (loop.index0 % 2 == 0) -%}
|
||||
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif -%}
|
||||
{%- 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 -%}
|
||||
75
config.json
Normal file
75
config.json
Normal file
@@ -0,0 +1,75 @@
|
||||
{
|
||||
"_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": "float16",
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"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_parameters": {
|
||||
"full_attention": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_attention": {
|
||||
"rope_theta": 10000,
|
||||
"rope_type": "default"
|
||||
}
|
||||
},
|
||||
"sliding_window": 512,
|
||||
"sliding_window_pattern": 6,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.13.1",
|
||||
"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": "5.13.1"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb277f4549e3edaa68313b5a885e409a90b1180afecb60a781f7ce4d6463d5a4
|
||||
size 1999810864
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
|
||||
size 33384567
|
||||
25
tokenizer_config.json
Normal file
25
tokenizer_config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"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,
|
||||
"local_files_only": 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>"
|
||||
},
|
||||
"pad_token": "<pad>",
|
||||
"processor_class": "Gemma3Processor",
|
||||
"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