初始化项目，由ModelHub XC社区提供模型
Model: exnivo/tinybrain-100m-instruct Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
assets/tinybrain-100m-instruct-banner.png filter=lfs diff=lfs merge=lfs -text
|
||||
assets/tinybrain-100m-instruct-banner-old.png filter=lfs diff=lfs merge=lfs -text
|
||||
454
README.md
Normal file
454
README.md
Normal file
@@ -0,0 +1,454 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- llama
|
||||
- text-generation
|
||||
- causal-lm
|
||||
- instruct
|
||||
- chat
|
||||
- sft
|
||||
- tinybrain
|
||||
- 100m
|
||||
- small-language-model
|
||||
- tiny-llm
|
||||
- english
|
||||
base_model:
|
||||
- exnivo/tinybrain-100m-base
|
||||
datasets:
|
||||
- exnivo/tinybrain-instruct-sft-200k
|
||||
---
|
||||
|
||||
<p align="center">
|
||||
<img
|
||||
src="https://huggingface.co/exnivo/tinybrain-100m-instruct/resolve/main/assets/tinybrain-100m-instruct-banner.png"
|
||||
alt="TinyBrain-100M Instruct — Instruction-tuned model for small LLMs"
|
||||
width="100%"
|
||||
/>
|
||||
</p>
|
||||
|
||||
# TinyBrain-100M Instruct
|
||||
|
||||
**A 103M parameter experimental chat/instruct model fine-tuned from TinyBrain-100M Base.**
|
||||
|
||||
TinyBrain-100M Instruct is a small instruction-tuned causal language model fine-tuned from [`exnivo/tinybrain-100m-base`](https://huggingface.co/exnivo/tinybrain-100m-base) using [`exnivo/tinybrain-instruct-sft-200k`](https://huggingface.co/datasets/exnivo/tinybrain-instruct-sft-200k).
|
||||
|
||||
This is a very small instruct model. It can answer simple prompts, explain basic ideas, give short plans, and sometimes show uncertainty behavior, but it is not a reliable general assistant. It may hallucinate, repeat text, fail at math, produce broken completions, or misunderstand prompts.
|
||||
|
||||
TinyBrain-100M Instruct was fine-tuned with a simple **User/Assistant** style format and **no system prompt**.
|
||||
|
||||
## Quick Start
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_id = "exnivo/tinybrain-100m-instruct"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||||
|
||||
prompt = "User: Explain photosynthesis in simple words.\nAssistant:"
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=80,
|
||||
do_sample=False,
|
||||
repetition_penalty=1.15,
|
||||
no_repeat_ngram_size=3,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
|
||||
text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
|
||||
answer = text.split("Assistant:", 1)[-1].strip()
|
||||
answer = answer.split("\nUser:", 1)[0].strip()
|
||||
|
||||
print(answer)
|
||||
```
|
||||
|
||||
## At a Glance
|
||||
|
||||
| Item | Details |
|
||||
|---|---|
|
||||
| Model type | Instruction-tuned causal language model |
|
||||
| Parameters | 103,385,856 |
|
||||
| Approx. size | 103.4M |
|
||||
| Architecture | LLaMA-style causal transformer |
|
||||
| Language | English |
|
||||
| Context length | 2048 tokens |
|
||||
| Vocabulary size | 24,000 |
|
||||
| Tokenizer | Custom TinyBrain tokenizer |
|
||||
| Base model | [`exnivo/tinybrain-100m-base`](https://huggingface.co/exnivo/tinybrain-100m-base) |
|
||||
| SFT dataset | [`exnivo/tinybrain-instruct-sft-200k`](https://huggingface.co/datasets/exnivo/tinybrain-instruct-sft-200k) |
|
||||
| Prompt style | `User:` / `Assistant:` |
|
||||
| System prompt | Not used during fine-tuning |
|
||||
|
||||
## Model Details
|
||||
|
||||
| Item | Value |
|
||||
|---|---|
|
||||
| Parameters | 103.4M |
|
||||
| Architecture | `llama` / `LlamaForCausalLM` |
|
||||
| Vocabulary size | 24,000 |
|
||||
| Context length | 2048 tokens |
|
||||
| Hidden size | 768 |
|
||||
| Intermediate size | 2048 |
|
||||
| Layers | 12 |
|
||||
| Attention heads | 12 |
|
||||
| Key/value heads | 12 |
|
||||
| Activation | SiLU |
|
||||
| RMS norm epsilon | `1e-05` |
|
||||
| Tied embeddings | true |
|
||||
| BOS token | `<|bos|>` |
|
||||
| EOS token | `<|eos|>` |
|
||||
| PAD token | `<|pad|>` |
|
||||
| Base model | [`exnivo/tinybrain-100m-base`](https://huggingface.co/exnivo/tinybrain-100m-base) |
|
||||
| SFT dataset | [`exnivo/tinybrain-instruct-sft-200k`](https://huggingface.co/datasets/exnivo/tinybrain-instruct-sft-200k) |
|
||||
|
||||
## Prompt Format
|
||||
|
||||
TinyBrain-100M Instruct was fine-tuned without a system prompt.
|
||||
|
||||
Use this simple format:
|
||||
|
||||
```text
|
||||
User: Your message here
|
||||
Assistant:
|
||||
```
|
||||
|
||||
Example:
|
||||
|
||||
```text
|
||||
User: Explain photosynthesis in simple words.
|
||||
Assistant:
|
||||
```
|
||||
|
||||
For best results:
|
||||
|
||||
- keep prompts short and direct
|
||||
- do not use a system prompt
|
||||
- use short generation lengths
|
||||
- prefer greedy or low-temperature generation
|
||||
- stop/cut the output if it starts a new `User:` turn
|
||||
|
||||
## Recommended Generation Settings
|
||||
|
||||
For stable short answers:
|
||||
|
||||
```python
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=80,
|
||||
do_sample=False,
|
||||
repetition_penalty=1.15,
|
||||
no_repeat_ngram_size=3,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
```
|
||||
|
||||
For slightly more varied answers:
|
||||
|
||||
```python
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=80,
|
||||
do_sample=True,
|
||||
temperature=0.5,
|
||||
top_p=0.85,
|
||||
repetition_penalty=1.15,
|
||||
no_repeat_ngram_size=3,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
```
|
||||
|
||||
For a very small model like this, long generations often become repetitive or unstable. Short completions usually work better.
|
||||
|
||||
## Example Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_id = "exnivo/tinybrain-100m-instruct"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||||
|
||||
def ask(message, max_new_tokens=80):
|
||||
prompt = f"User: {message}\nAssistant:"
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=max_new_tokens,
|
||||
do_sample=False,
|
||||
repetition_penalty=1.15,
|
||||
no_repeat_ngram_size=3,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
|
||||
text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
answer = text.split("Assistant:", 1)[-1].strip()
|
||||
answer = answer.split("\nUser:", 1)[0].strip()
|
||||
return answer
|
||||
|
||||
print(ask("Explain gravity in simple words."))
|
||||
```
|
||||
|
||||
## Training Data
|
||||
|
||||
TinyBrain-100M Instruct was fine-tuned on:
|
||||
|
||||
[`exnivo/tinybrain-instruct-sft-200k`](https://huggingface.co/datasets/exnivo/tinybrain-instruct-sft-200k)
|
||||
|
||||
The SFT dataset contains **196,668 rows** of English instruction/chat examples focused on short, learnable assistant behavior.
|
||||
|
||||
Dataset categories include:
|
||||
|
||||
| Category | Rows | Percent |
|
||||
|---|---:|---:|
|
||||
| `source_grounded_education_factual` | 49,882 | 25.36% |
|
||||
| `math_reasoning` | 37,611 | 19.12% |
|
||||
| `clean_conversation` | 34,257 | 17.42% |
|
||||
| `messy_idea_to_plan` | 29,978 | 15.24% |
|
||||
| `simplify_explain` | 19,990 | 10.16% |
|
||||
| `honesty_uncertainty` | 14,957 | 7.61% |
|
||||
| `simple_coding` | 9,993 | 5.08% |
|
||||
|
||||
The dataset was designed for small models and uses short assistant responses across education, basic math, planning, simplification, simple coding, clean conversation, and uncertainty behavior.
|
||||
|
||||
## Relationship to TinyBrain
|
||||
|
||||
TinyBrain is a small LLM project focused on compact datasets, small base models, and instruction-tuned models.
|
||||
|
||||
| Stage | Repository | Purpose |
|
||||
|---|---|---|
|
||||
| Pretraining corpus | [`exnivo/tinybrain-pretrain-corpus-2b`](https://huggingface.co/datasets/exnivo/tinybrain-pretrain-corpus-2b) | Base language model training data |
|
||||
| Base model | [`exnivo/tinybrain-100m-base`](https://huggingface.co/exnivo/tinybrain-100m-base) | Small causal LM trained from scratch |
|
||||
| SFT dataset | [`exnivo/tinybrain-instruct-sft-200k`](https://huggingface.co/datasets/exnivo/tinybrain-instruct-sft-200k) | Instruction/chat fine-tuning data |
|
||||
| Instruct model | [`exnivo/tinybrain-100m-instruct`](https://huggingface.co/exnivo/tinybrain-100m-instruct) | Chat/instruct model fine-tuned from the base model |
|
||||
|
||||
Pipeline:
|
||||
|
||||
```text
|
||||
TinyBrain Pretrain Corpus 2B
|
||||
↓
|
||||
TinyBrain-100M Base
|
||||
↓
|
||||
TinyBrain Instruct 200K
|
||||
↓
|
||||
TinyBrain-100M Instruct
|
||||
```
|
||||
|
||||
## Expected Behavior
|
||||
|
||||
TinyBrain-100M Instruct can sometimes handle:
|
||||
|
||||
- simple explanations
|
||||
- short educational questions
|
||||
- basic planning
|
||||
- simple rewriting/simplification
|
||||
- simple coding prompts
|
||||
- some uncertainty/refusal-style prompts
|
||||
- casual assistant-like responses
|
||||
|
||||
Example prompt:
|
||||
|
||||
```text
|
||||
User: Explain photosynthesis in simple words.
|
||||
Assistant:
|
||||
```
|
||||
|
||||
Possible output style:
|
||||
|
||||
```text
|
||||
Photosynthesis is how plants make their own food using sunlight, water, and air. They turn these into sugar and oxygen.
|
||||
```
|
||||
|
||||
Because this is a very small model, outputs may be unstable. It can repeat, drift, or produce broken text, especially with long generations or higher sampling temperatures.
|
||||
|
||||
## Evaluation Notes
|
||||
|
||||
A lightweight local report confirmed the model architecture and parameter count:
|
||||
|
||||
| Metric | Value |
|
||||
|---|---:|
|
||||
| Total parameters | 103,385,856 |
|
||||
| Trainable parameters | 103,385,856 |
|
||||
| Approx. parameters | 103.4M |
|
||||
|
||||
Manual prompt tests showed that the model behaves better with the plain `User:` / `Assistant:` format than with custom chat-special-token formatting.
|
||||
|
||||
The model can produce useful short answers for some prompts, but it still performs poorly on reliable math, longer reasoning, and some instruction-following tasks.
|
||||
|
||||
This should be treated as an experimental small-model checkpoint, not a benchmark-grade assistant.
|
||||
|
||||
## Intended Use
|
||||
|
||||
TinyBrain-100M Instruct is intended for:
|
||||
|
||||
- small-model experiments
|
||||
- local lightweight assistant tests
|
||||
- instruction-tuning research
|
||||
- comparing base vs instruct behavior
|
||||
- educational model experiments
|
||||
- studying tiny LLM limitations
|
||||
- continued fine-tuning
|
||||
- dataset/model pipeline demos
|
||||
|
||||
This model is useful for exploring how much instruction-following behavior can be added to a small 100M-parameter model.
|
||||
|
||||
## Not Intended For
|
||||
|
||||
Do not rely on this model for:
|
||||
|
||||
- medical advice
|
||||
- legal advice
|
||||
- financial advice
|
||||
- emergency decisions
|
||||
- safety-critical systems
|
||||
- factual authority
|
||||
- current news or live information
|
||||
- advanced math
|
||||
- advanced coding
|
||||
- long-form reasoning
|
||||
- production assistant use without further training and evaluation
|
||||
|
||||
This is an experimental model and should not be used as a source of truth.
|
||||
|
||||
## Strengths
|
||||
|
||||
TinyBrain-100M Instruct is useful because it is:
|
||||
|
||||
- small
|
||||
- lightweight
|
||||
- easy to run locally
|
||||
- fine-tuned from a matching TinyBrain base model
|
||||
- trained on a public TinyBrain SFT dataset
|
||||
- designed for short assistant-style responses
|
||||
- useful for base-vs-instruct comparison
|
||||
- good for studying tiny model behavior
|
||||
|
||||
## Limitations
|
||||
|
||||
TinyBrain-100M Instruct has major limitations.
|
||||
|
||||
The model may:
|
||||
|
||||
- hallucinate facts
|
||||
- fail simple math
|
||||
- repeat words or phrases
|
||||
- produce broken text
|
||||
- drift off-topic
|
||||
- answer too briefly
|
||||
- misunderstand prompts
|
||||
- generate unreliable code
|
||||
- fail at longer reasoning
|
||||
- fail refusal or safety behavior
|
||||
- continue into fake new user turns
|
||||
|
||||
For best results, keep prompts short and use short generation lengths.
|
||||
|
||||
## Known Weaknesses
|
||||
|
||||
Based on local testing, this model is especially weak at:
|
||||
|
||||
- reliable arithmetic
|
||||
- robust coding
|
||||
- long answers
|
||||
- multi-step reasoning
|
||||
- clean formatting
|
||||
- high-temperature sampling
|
||||
- long context use
|
||||
|
||||
It may answer simple educational prompts better than math or code prompts.
|
||||
|
||||
## Suggested Evaluation
|
||||
|
||||
Recommended checks:
|
||||
|
||||
- short factual prompts
|
||||
- simple explanation prompts
|
||||
- basic math prompts
|
||||
- correction prompts
|
||||
- refusal/uncertainty prompts
|
||||
- repetition tests
|
||||
- prompt-format tests
|
||||
- base vs instruct comparison
|
||||
- SFT dataset overfitting checks
|
||||
- generation temperature sensitivity
|
||||
|
||||
Example prompts:
|
||||
|
||||
```text
|
||||
User: Explain gravity in simple words.
|
||||
Assistant:
|
||||
```
|
||||
|
||||
```text
|
||||
User: What is 17 + 25?
|
||||
Assistant:
|
||||
```
|
||||
|
||||
```text
|
||||
User: What will the weather be tomorrow in my city?
|
||||
Assistant:
|
||||
```
|
||||
|
||||
```text
|
||||
User: Give me 3 quick tips to keep my room tidy.
|
||||
Assistant:
|
||||
```
|
||||
|
||||
```text
|
||||
User: Write a simple Python function that reverses a string.
|
||||
Assistant:
|
||||
```
|
||||
|
||||
## Training
|
||||
|
||||
TinyBrain-100M Instruct was fine-tuned from:
|
||||
|
||||
[`exnivo/tinybrain-100m-base`](https://huggingface.co/exnivo/tinybrain-100m-base)
|
||||
|
||||
using:
|
||||
|
||||
[`exnivo/tinybrain-instruct-sft-200k`](https://huggingface.co/datasets/exnivo/tinybrain-instruct-sft-200k)
|
||||
|
||||
The base model was trained from scratch on [`exnivo/tinybrain-pretrain-corpus-2b`](https://huggingface.co/datasets/exnivo/tinybrain-pretrain-corpus-2b).
|
||||
|
||||
## Citation
|
||||
|
||||
If you use this model, you can cite it as:
|
||||
|
||||
```bibtex
|
||||
@misc{tinybrain_100m_instruct,
|
||||
title = {TinyBrain-100M Instruct},
|
||||
author = {exnivo},
|
||||
year = {2026},
|
||||
publisher = {Hugging Face},
|
||||
howpublished = {\url{https://huggingface.co/exnivo/tinybrain-100m-instruct}}
|
||||
}
|
||||
```
|
||||
|
||||
## Related Repositories
|
||||
|
||||
- Pretraining corpus: [`exnivo/tinybrain-pretrain-corpus-2b`](https://huggingface.co/datasets/exnivo/tinybrain-pretrain-corpus-2b)
|
||||
- Base model: [`exnivo/tinybrain-100m-base`](https://huggingface.co/exnivo/tinybrain-100m-base)
|
||||
- SFT dataset: [`exnivo/tinybrain-instruct-sft-200k`](https://huggingface.co/datasets/exnivo/tinybrain-instruct-sft-200k)
|
||||
- Instruct model: [`exnivo/tinybrain-100m-instruct`](https://huggingface.co/exnivo/tinybrain-100m-instruct)
|
||||
|
||||
## License
|
||||
|
||||
This model is released under the Apache 2.0 license.
|
||||
|
||||
The SFT dataset and pretraining corpus are mixed-source datasets and may have their own licensing considerations. Users should review the dataset cards and upstream source metadata before commercial use.
|
||||
|
||||
## Disclaimer
|
||||
|
||||
TinyBrain-100M Instruct is an experimental tiny instruction-tuned language model. It may produce incorrect, biased, unsafe, nonsensical, or misleading outputs.
|
||||
|
||||
Do not use this model for high-stakes decisions or as a reliable source of factual information.
|
||||
0
assets/.gitkeep
Normal file
0
assets/.gitkeep
Normal file
3
assets/tinybrain-100m-instruct-banner-old.png
Normal file
3
assets/tinybrain-100m-instruct-banner-old.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7bad48b7741fa2dba5e24ef25c8d72f8cab8e8199e617c9387553fb572d07d26
|
||||
size 991199
|
||||
3
assets/tinybrain-100m-instruct-banner.png
Normal file
3
assets/tinybrain-100m-instruct-banner.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ff904f7cd1f872d60d7ee82d28a64502f88d374f5a71039fc09e8799f04915f
|
||||
size 1133741
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 768,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2048,
|
||||
"max_position_embeddings": 2048,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 12,
|
||||
"num_key_value_heads": 12,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.12.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 24000
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.12.1",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f9e0f3883b4b5c76643f2a3b67a86d049bf27c98e80b73a2bb9557a4e598217
|
||||
size 206783968
|
||||
10
tinybrain_sft_meta.json
Normal file
10
tinybrain_sft_meta.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"step": 522,
|
||||
"val_loss": 2.2578155994415283,
|
||||
"base_model": "exnivo/tinybrain-100m-base",
|
||||
"dataset": "exnivo/tinybrain-instruct",
|
||||
"batch_size": 100,
|
||||
"block_size": 1024,
|
||||
"epochs": 3,
|
||||
"lr": 7e-05
|
||||
}
|
||||
119086
tokenizer.json
Normal file
119086
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
22
tokenizer_config.json
Normal file
22
tokenizer_config.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|bos|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|eos|>",
|
||||
"extra_special_tokens": [
|
||||
"<|user|>",
|
||||
"<|assistant|>",
|
||||
"<|system|>",
|
||||
"<|end|>",
|
||||
"<|tool|>",
|
||||
"<|tool_call|>",
|
||||
"<|tool_result|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "<|pad|>",
|
||||
"padding_side": "right",
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"truncation_side": "right"
|
||||
}
|
||||
Reference in New Issue
Block a user