FlameF0X/Qwen2-0.2B-it
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: FlameF0X/Qwen2-0.2B-it
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-25 05:09:09 +08:00
commit ca47e0c5e7
16 changed files with 602 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.eval_results/mmlu_pro.yaml Normal file
View File

@@ -0,0 +1,8 @@
- dataset:
id: TIGER-Lab/MMLU-Pro
task_id: mmlu_pro
value: 4.0
source:
url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
name: Model Card
user: FlameF0X

17
.eval_results/results.yaml Normal file
View File

@@ -0,0 +1,17 @@
- dataset:
id: TIGER-Lab/MMLU-Pro
task_id: mmlu_pro
value: 4.0
source:
url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
name: Model Card
user: FlameF0X
- dataset:
id: openai/gsm8k
task_id: gsm8k
value: 2.0
source:
url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
name: Model Card
user: FlameF0X

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

126
README.md Normal file
View File

@@ -0,0 +1,126 @@
---
library_name: transformers
base_model:
- FlameF0X/Qwen2-0.2B-pt
license: apache-2.0
datasets:
- Salesforce/wikitext
- roneneldan/TinyStories
- FlameF0X/arXiv-AI-ML
- Skylion007/openwebtext
- flytech/python-codes-25k
- bookcorpus/bookcorpus
- HuggingFaceH4/ultrachat_200k
- openai/gsm8k
- microsoft/orca-math-word-problems-200k
- laion/OIG
- microsoft/wiki_qa
metrics:
- accuracy
model-index:
- name: FlameF0X/Qwen2-0.2B-it
results:
- task:
type: text-generation
name: Text Generation
dataset:
id: openai/gsm8k
name: GSM8K
type: gsm8k
config: main
split: test
metrics:
- name: Accuracy
type: accuracy
value: 2.00
verified: false
source:
name: Local Benchmark
url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
- task:
type: text-generation
name: Text Generation
dataset:
id: TIGER-Lab/MMLU-Pro
name: MMLU-Pro
type: TIGER-Lab/MMLU-Pro
config: default
split: test
metrics:
- name: Accuracy
type: accuracy
value: 4.00
verified: false
source:
name: Local Benchmark
url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
---
## Evaluation Results
| Benchmark | Score |
|-----------|-------|
| GSM8K (test) | 2.00% |
| MMLU-Pro (test) | 4.00% |
> Results obtained via local evaluation. Given the model size (0.2B parameters), low benchmark scores are expected.
## Model Usage
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_path = "FlameF0X/Qwen2-0.2B-it"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype="auto",
device_map="auto",
trust_remote_code=True
)
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain how a transformer model works in one sentence."}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=128,
do_sample=True,
temperature=0.7
)
generated_ids = [
output_ids[len(input_ids):]
for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(f"--- Assistant Response ---\n{response}")
```
## Training Data
This model was instruction-tuned on a mixture of:
- `Salesforce/wikitext` — General text
- `roneneldan/TinyStories` — Short story generation
- `FlameF0X/arXiv-AI-ML` — AI/ML research papers
- `Skylion007/openwebtext` — Web text
- `flytech/python-codes-25k` — Python code
- `bookcorpus/bookcorpus` — Books
- `HuggingFaceH4/ultrachat_200k` — Instruction following
- `openai/gsm8k` — Math reasoning
- `microsoft/orca-math-word-problems-200k` — Math word problems
- `laion/OIG` — Open instruction generalist
- `microsoft/wiki_qa` — Question answering

1
chat_template.jinja Normal file
View File

@@ -0,0 +1 @@
{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}

41
config.json Normal file
View File

@@ -0,0 +1,41 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "float32",
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 1376,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 2048,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 8,
"num_hidden_layers": 8,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.2.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"_from_model_config": true,
"eos_token_id": 151643,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 151643,
"transformers_version": "5.2.0",
"use_cache": true
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f34ca4b7fea430ee68446e9d66f21dc0db8d5c674a3ba30b6b634694e8d9e501
size 723612256

3
optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de8b2cf2a988ec7f7c7f403ba328be18f8874faaf5ecc21164260f960eb24b0f
size 1447288075

3
rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3
size 14645

3
scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
size 1383

3
scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8918e26db947366e457e93daaf6ae845d9aef0ef762ad16d34c2fab1781df115
size 1465

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d429fe753aea0ff87a94e86396d5508abb0d1d0e1f7a0d47c787ff72e0bf2691
size 11422170

29
tokenizer_config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"is_local": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

314
trainer_state.json Normal file
View File

@@ -0,0 +1,314 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.807384615384615,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.24615384615384617,
"grad_norm": 0.09971032291650772,
"learning_rate": 7.921600000000001e-05,
"loss": 3.8301455688476564,
"step": 50
},
{
"epoch": 0.49230769230769234,
"grad_norm": 0.0911579355597496,
"learning_rate": 7.8416e-05,
"loss": 3.0332159423828124,
"step": 100
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.10190442204475403,
"learning_rate": 7.7616e-05,
"loss": 2.7591339111328126,
"step": 150
},
{
"epoch": 0.9846153846153847,
"grad_norm": 0.09316737949848175,
"learning_rate": 7.6816e-05,
"loss": 2.617864074707031,
"step": 200
},
{
"epoch": 1.2264615384615385,
"grad_norm": 0.08559751510620117,
"learning_rate": 7.601600000000001e-05,
"loss": 2.3154002380371095,
"step": 250
},
{
"epoch": 1.4726153846153847,
"grad_norm": 0.0818333625793457,
"learning_rate": 7.5216e-05,
"loss": 2.227242126464844,
"step": 300
},
{
"epoch": 1.7187692307692308,
"grad_norm": 0.09082052856683731,
"learning_rate": 7.441600000000001e-05,
"loss": 2.1838539123535154,
"step": 350
},
{
"epoch": 1.964923076923077,
"grad_norm": 0.08575436472892761,
"learning_rate": 7.361600000000001e-05,
"loss": 2.1341651916503905,
"step": 400
},
{
"epoch": 2.206769230769231,
"grad_norm": 0.08966775238513947,
"learning_rate": 7.2816e-05,
"loss": 1.9519345092773437,
"step": 450
},
{
"epoch": 2.452923076923077,
"grad_norm": 0.08918383717536926,
"learning_rate": 7.201600000000001e-05,
"loss": 1.8568724060058595,
"step": 500
},
{
"epoch": 2.699076923076923,
"grad_norm": 0.09143362194299698,
"learning_rate": 7.1216e-05,
"loss": 1.8383006286621093,
"step": 550
},
{
"epoch": 2.9452307692307693,
"grad_norm": 0.0969746857881546,
"learning_rate": 7.0416e-05,
"loss": 1.8297712707519531,
"step": 600
},
{
"epoch": 3.187076923076923,
"grad_norm": 0.09824724495410919,
"learning_rate": 6.9616e-05,
"loss": 1.6545506286621094,
"step": 650
},
{
"epoch": 3.4332307692307693,
"grad_norm": 0.08493440598249435,
"learning_rate": 6.8816e-05,
"loss": 1.6011067199707032,
"step": 700
},
{
"epoch": 3.6793846153846155,
"grad_norm": 0.08676321804523468,
"learning_rate": 6.801600000000001e-05,
"loss": 1.5964797973632812,
"step": 750
},
{
"epoch": 3.9255384615384616,
"grad_norm": 0.09471355378627777,
"learning_rate": 6.7216e-05,
"loss": 1.5877139282226562,
"step": 800
},
{
"epoch": 4.1673846153846155,
"grad_norm": 0.08782424032688141,
"learning_rate": 6.641600000000001e-05,
"loss": 1.4405186462402344,
"step": 850
},
{
"epoch": 4.413538461538462,
"grad_norm": 0.09666605293750763,
"learning_rate": 6.5616e-05,
"loss": 1.383701171875,
"step": 900
},
{
"epoch": 4.659692307692308,
"grad_norm": 0.10380911082029343,
"learning_rate": 6.481600000000001e-05,
"loss": 1.375392608642578,
"step": 950
},
{
"epoch": 4.905846153846154,
"grad_norm": 0.10152668505907059,
"learning_rate": 6.4016e-05,
"loss": 1.3678237915039062,
"step": 1000
},
{
"epoch": 5.147692307692307,
"grad_norm": 0.102939173579216,
"learning_rate": 6.321600000000001e-05,
"loss": 1.257767333984375,
"step": 1050
},
{
"epoch": 5.3938461538461535,
"grad_norm": 0.09689474105834961,
"learning_rate": 6.241600000000001e-05,
"loss": 1.179140625,
"step": 1100
},
{
"epoch": 5.64,
"grad_norm": 0.09813547879457474,
"learning_rate": 6.1616e-05,
"loss": 1.1883023071289063,
"step": 1150
},
{
"epoch": 5.886153846153846,
"grad_norm": 0.10634688287973404,
"learning_rate": 6.0816e-05,
"loss": 1.196829605102539,
"step": 1200
},
{
"epoch": 6.128,
"grad_norm": 0.10477212816476822,
"learning_rate": 6.0016e-05,
"loss": 1.0858740234375,
"step": 1250
},
{
"epoch": 6.374153846153846,
"grad_norm": 0.10455155372619629,
"learning_rate": 5.9216000000000004e-05,
"loss": 0.9896931457519531,
"step": 1300
},
{
"epoch": 6.6203076923076924,
"grad_norm": 0.10506019741296768,
"learning_rate": 5.8416000000000004e-05,
"loss": 1.0163351440429687,
"step": 1350
},
{
"epoch": 6.866461538461539,
"grad_norm": 0.1090712919831276,
"learning_rate": 5.7616e-05,
"loss": 1.0064225006103515,
"step": 1400
},
{
"epoch": 7.108307692307692,
"grad_norm": 0.10628747940063477,
"learning_rate": 5.6816000000000006e-05,
"loss": 0.931029052734375,
"step": 1450
},
{
"epoch": 7.354461538461538,
"grad_norm": 0.1018829494714737,
"learning_rate": 5.601600000000001e-05,
"loss": 0.8393967437744141,
"step": 1500
},
{
"epoch": 7.600615384615384,
"grad_norm": 0.11559069901704788,
"learning_rate": 5.521600000000001e-05,
"loss": 0.8411316680908203,
"step": 1550
},
{
"epoch": 7.8467692307692305,
"grad_norm": 0.12172011286020279,
"learning_rate": 5.441600000000001e-05,
"loss": 0.8445599365234375,
"step": 1600
},
{
"epoch": 8.088615384615384,
"grad_norm": 0.09611531347036362,
"learning_rate": 5.3616e-05,
"loss": 0.7935149383544922,
"step": 1650
},
{
"epoch": 8.334769230769231,
"grad_norm": 0.11105120927095413,
"learning_rate": 5.2816000000000004e-05,
"loss": 0.6863140106201172,
"step": 1700
},
{
"epoch": 8.580923076923076,
"grad_norm": 0.10133285075426102,
"learning_rate": 5.2016000000000005e-05,
"loss": 0.6949832153320312,
"step": 1750
},
{
"epoch": 8.827076923076923,
"grad_norm": 0.11194281280040741,
"learning_rate": 5.1216000000000006e-05,
"loss": 0.7070323944091796,
"step": 1800
},
{
"epoch": 9.068923076923078,
"grad_norm": 0.093862384557724,
"learning_rate": 5.0416e-05,
"loss": 0.6766038513183594,
"step": 1850
},
{
"epoch": 9.315076923076923,
"grad_norm": 0.1024981439113617,
"learning_rate": 4.9616e-05,
"loss": 0.5633995056152343,
"step": 1900
},
{
"epoch": 9.56123076923077,
"grad_norm": 0.10483216494321823,
"learning_rate": 4.8816e-05,
"loss": 0.5755315399169922,
"step": 1950
},
{
"epoch": 9.807384615384615,
"grad_norm": 0.11396331340074539,
"learning_rate": 4.8016e-05,
"loss": 0.5865091705322265,
"step": 2000
}
],
"logging_steps": 50,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 25,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.019225655836672e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:197af5fb66d4f0b05823de4e1b82d51e93a46f42124f1586c8e67d8a8a0dfbdc
size 5201