初始化项目，由ModelHub XC社区提供模型
Model: littlelearner/unfiltered-1.3b-grpo-math-expert Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
57
README.md
Normal file
57
README.md
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
license: other
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- qwen3
|
||||
- text-generation
|
||||
- littlelearner
|
||||
- unbounded
|
||||
- instruct
|
||||
- reinforcement-learning
|
||||
---
|
||||
|
||||
# unfiltered-1.3b-grpo-math-expert
|
||||
|
||||
1.36B fully-unbounded chat model post-trained with GRPO on top of SFT.
|
||||
|
||||
Part of the [**LittleLearner**](https://arxiv.org/abs/2608.13545) scale-up study (*pedagogically-controlled knowledge exposure*): Qwen3 dense LMs trained on a corpus filtered to U.S. K-5 material (**bounded**) vs an unfiltered FineWeb-Edu corpus (**unbounded**), to measure what an interpretable knowledge boundary costs and grants.
|
||||
|
||||
Note: This checkpoint was post-trained with GRPO on mathematical reasoning tasks to probe achievable performance on MathCAMPS. As a result, its behavior is specialized toward mathematical reasoning and may not preserve general-purpose chat capabilities; responses may also exhibit a tendency toward math-oriented reasoning or output.
|
||||
|
||||
## Model
|
||||
- **Architecture:** Qwen3 dense (`Qwen3ForCausalLM`).
|
||||
- **Size:** 1.358B params, hidden 2048, 26 layers, 16 query / 8 KV heads, FFN 5632. **Context:** 4096.
|
||||
- **Tokenizer:** custom 64k byte-level BPE with per-digit splitting (ChatML special tokens).
|
||||
- **Pretraining:** 88B tokens on **unfiltered** FineWeb-Edu (score >= 2, no grade filter). WSD schedule, sharded Muon, MXFP8, Megatron-Core on 8xB200.
|
||||
- **SFT:** supervised fine-tuned on unbounded chat data (lr 1e-5, 3 epochs).
|
||||
- **RL (GRPO):** segmented policy re-banding on a verifiable-answer pool: temperature-1.0 segments to a plateau, then one segment at temperature 1.3 (a one-shot unlock).
|
||||
|
||||
## Evaluation
|
||||
MathCAMPS:
|
||||
- K-5 pass@64 **70.6** / pass@1 **45.7**
|
||||
- beyond-K-5 pass@64 **45.6** / pass@1 **16.5**
|
||||
|
||||
## Usage
|
||||
```python
|
||||
# transformers (chat)
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
repo = "manueldeprada/littlelearner-1.3b-unbounded-grpo"
|
||||
tok = AutoTokenizer.from_pretrained(repo)
|
||||
model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="cuda")
|
||||
msgs = [{"role": "user", "content": "Liam has 3 apples and buys 4 more. How many apples does he have?"}]
|
||||
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
||||
out = model.generate(ids)
|
||||
print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
```python
|
||||
# vLLM
|
||||
from vllm import LLM
|
||||
repo = "manueldeprada/littlelearner-1.3b-unbounded-grpo"
|
||||
llm = LLM(repo)
|
||||
msgs = [{"role": "user", "content": "Liam has 3 apples and buys 4 more. How many apples does he have?"}]
|
||||
print(llm.chat(msgs)[0].outputs[0].text)
|
||||
```
|
||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal 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 -%}
|
||||
66
config.json
Normal file
66
config.json
Normal file
@@ -0,0 +1,66 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": [
|
||||
3,
|
||||
0
|
||||
],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5632,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 4096,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 26,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.2.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 64000,
|
||||
"rope_theta": 1000000.0,
|
||||
"torch_dtype": "bfloat16"
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"eos_token_id": [
|
||||
3,
|
||||
0
|
||||
],
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.2.0",
|
||||
"use_cache": true,
|
||||
"max_new_tokens": 512
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:60f0f0e621a6e9318e2caf88e63e3a480d4e7d154af0a05a816fa63b3de5ef40
|
||||
size 2716075264
|
||||
320361
tokenizer.json
Normal file
320361
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
12
tokenizer_config.json
Normal file
12
tokenizer_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"add_prefix_space": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"eos_token": "<|im_end|>",
|
||||
"is_local": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"chat_template": "{%- for message in messages -%}\n{{- '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>\\n' -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}{{- '<|im_start|>assistant\\n' -}}{%- endif -%}\n"
|
||||
}
|
||||
Reference in New Issue
Block a user