初始化项目，由ModelHub XC社区提供模型
Model: barbaroo/gptsw3-6.7B-translation-en-fo 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
|
||||
167
README.md
Normal file
167
README.md
Normal file
@@ -0,0 +1,167 @@
|
||||
---
|
||||
base_model: AI-Sweden-Models/gpt-sw3-6.7b-v2
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- barbaroo/Sprotin_parallel
|
||||
- barbaroo/fo_en_synthetic
|
||||
language:
|
||||
- en
|
||||
- fo
|
||||
metrics:
|
||||
- bleu
|
||||
- chrf
|
||||
- bertscore
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Model Card: English–Faroese Translation (Merged Model)
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
- **Developed by:** Barbara Scalvini
|
||||
- **Model type:** Fully merged model for **English → Faroese** translation
|
||||
- **Languages:** English, Faroese
|
||||
- **License:** Inherits license from the base model (GPT-SW3 6.7B)
|
||||
- **Finetuned from:** [AI-Sweden-Models/gpt-sw3-6.7b-v2](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b-v2)
|
||||
- **Library:** [Transformers](https://github.com/huggingface/transformers)
|
||||
|
||||
This model is the **merged version** of the PEFT adapter [`barbaroo/gptsw3_translate_synth_6.7B`](https://huggingface.co/barbaroo/gptsw3_translate_synth_6.7B) with its base model.
|
||||
|
||||
---
|
||||
|
||||
## Uses
|
||||
|
||||
### Direct Use
|
||||
- English → Faroese machine translation.
|
||||
|
||||
### Downstream Use
|
||||
- Can be integrated into **multilingual NLP pipelines** or localization workflows.
|
||||
|
||||
### Out-of-Scope Use
|
||||
- Languages other than English or Faroese.
|
||||
- Tasks like summarization, classification, or dialogue without further fine-tuning.
|
||||
|
||||
---
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
- As with all translation models, may reflect **biases** from the training corpora.
|
||||
- Outputs should be **carefully validated** for sensitive or high-stakes domains.
|
||||
|
||||
---
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
```python
|
||||
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
||||
import re
|
||||
import pandas as pd
|
||||
|
||||
# Model repo
|
||||
MODEL_NAME = "barbaroo/gptsw3-6.7B-translation-en-fo"
|
||||
|
||||
# Quantization config (8-bit)
|
||||
bnb_config = BitsAndBytesConfig(
|
||||
load_in_8bit=True
|
||||
)
|
||||
|
||||
# Initialize tokenizer & model
|
||||
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
MODEL_NAME,
|
||||
quantization_config=bnb_config,
|
||||
device_map="auto",
|
||||
)
|
||||
model.eval()
|
||||
|
||||
# Alpaca-style prompt template
|
||||
alpaca_prompt = """
|
||||
|
||||
### Instruction:
|
||||
{}
|
||||
|
||||
### Input:
|
||||
{}
|
||||
|
||||
### Response:
|
||||
{}"""
|
||||
|
||||
EOS_TOKEN = tokenizer.eos_token
|
||||
print("EOS token:", EOS_TOKEN)
|
||||
|
||||
# Example sentences
|
||||
sentences = ["I love Faroese!"]
|
||||
translations = []
|
||||
|
||||
for sentence in sentences:
|
||||
inputs = tokenizer(
|
||||
[
|
||||
alpaca_prompt.format(
|
||||
"Translate this sentence from English to Faroese:",
|
||||
sentence,
|
||||
"",
|
||||
)
|
||||
],
|
||||
return_tensors="pt"
|
||||
).to("cuda")
|
||||
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=500,
|
||||
use_cache=True,
|
||||
do_sample=True,
|
||||
temperature=0.1,
|
||||
top_p=1,
|
||||
)
|
||||
|
||||
output_string = tokenizer.batch_decode(outputs, skip_special_tokens=False)[0]
|
||||
|
||||
try:
|
||||
response = output_string.split("Response:\n", 1)[1]
|
||||
translation = response.replace(EOS_TOKEN, "")
|
||||
except IndexError:
|
||||
translation = ""
|
||||
|
||||
translations.append(translation)
|
||||
print(translation)
|
||||
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
- [barbaroo/Sprotin_parallel](https://huggingface.co/datasets/barbaroo/Sprotin_parallel)
|
||||
- [barbaroo/fo_en_synthetic](https://huggingface.co/datasets/barbaroo/fo_en_synthetic)
|
||||
|
||||
### Procedure
|
||||
- Initially trained as a **PEFT adapter** using Alpaca-style prompts.
|
||||
- Then **merged with the base GPT-SW3 6.7B model** to produce this standalone version.
|
||||
|
||||
**Hyperparameters:**
|
||||
- Epochs: 3 (early stopping on validation loss)
|
||||
- Batch Size: 2 (with 4 gradient accumulation steps)
|
||||
- Learning Rate: 2e-4
|
||||
- Optimizer: AdamW with LR scheduler + warm-up
|
||||
|
||||
---
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Test Data
|
||||
- FLORES-200 benchmark (~1012 English–Faroese pairs).
|
||||
|
||||
### Metrics
|
||||
- **BLEU:** 19.8
|
||||
- **chrF:** 52.4
|
||||
|
||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"apply_query_key_layer_scaling": true,
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 1,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 3,
|
||||
"initializer_range": 0.01,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 2048,
|
||||
"n_embd": 4096,
|
||||
"n_head": 32,
|
||||
"n_inner": 16384,
|
||||
"n_layer": 32,
|
||||
"n_positions": 2048,
|
||||
"normalize_attention_scores": true,
|
||||
"pad_token_id": 0,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"tokenizer_class": "GPTSw3Tokenizer",
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.50.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 64000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 3,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.50.3"
|
||||
}
|
||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5a00293adf4497e16d8115d15eb69ccfd999e0fab04c0b3e85074f7eadded849
|
||||
size 4841281680
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:af66310204b2a05b15f3d8549efc092ebf18e5f8c0954a2cce0fbede60bec9dc
|
||||
size 4833123736
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d96fb5688917fd6f1b801ab0ba98abf8f1b533654e5e214d1d12dea84d8b4557
|
||||
size 4833123800
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:37addc472d1915e688f8beeb7a1a9500e3023f8a9e45af21c76212ddc5eb3288
|
||||
size 4833123800
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e7bf0636d79e7e4752bc78ffddaff53ee117d0eff0cc3a956923b1856d8fae31
|
||||
size 4833123800
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47d2bd6f8757029e084a52f314a90340d29f57f4447150b11007b10f1d9d01ff
|
||||
size 2685046912
|
||||
395
model.safetensors.index.json
Normal file
395
model.safetensors.index.json
Normal file
@@ -0,0 +1,395 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26858782720
|
||||
},
|
||||
"weight_map": {
|
||||
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.attn.c_attn.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.attn.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.ln_1.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.ln_1.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.ln_2.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.ln_2.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.attn.c_attn.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.attn.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.ln_1.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.ln_1.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.ln_2.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.ln_2.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.10.attn.c_attn.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.attn.c_attn.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.attn.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.attn.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.ln_1.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.ln_1.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.ln_2.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.ln_2.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.attn.c_attn.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.attn.c_attn.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.attn.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.attn.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.ln_1.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.ln_1.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.ln_2.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.ln_2.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.attn.c_attn.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.attn.c_attn.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.attn.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.attn.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.ln_1.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.ln_1.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.ln_2.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.ln_2.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.attn.c_attn.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.attn.c_attn.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.attn.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.attn.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.ln_1.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.ln_1.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.ln_2.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.ln_2.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.attn.c_attn.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.attn.c_attn.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.attn.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.attn.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.ln_1.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.ln_1.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.ln_2.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.ln_2.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.attn.c_attn.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.attn.c_attn.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.attn.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.attn.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.ln_1.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.ln_1.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.ln_2.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.ln_2.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.attn.c_attn.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.attn.c_attn.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.attn.c_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.attn.c_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.ln_1.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.ln_1.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.ln_2.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.ln_2.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.attn.c_attn.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.attn.c_attn.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.attn.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.attn.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.ln_1.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.ln_1.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.ln_2.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.ln_2.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.attn.c_attn.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.attn.c_attn.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.attn.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.attn.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.ln_1.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.ln_1.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.ln_2.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.ln_2.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.attn.c_attn.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.attn.c_attn.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.attn.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.attn.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.ln_1.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.ln_1.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.ln_2.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.ln_2.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.attn.c_attn.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.attn.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.ln_1.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.ln_1.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.ln_2.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.ln_2.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.20.attn.c_attn.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.attn.c_attn.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.attn.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.attn.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.ln_1.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.ln_1.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.ln_2.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.ln_2.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.attn.c_attn.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.attn.c_attn.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.attn.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.attn.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.ln_1.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.ln_1.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.ln_2.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.ln_2.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.attn.c_attn.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.attn.c_attn.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.attn.c_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.attn.c_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.ln_1.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.ln_1.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.ln_2.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.ln_2.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.attn.c_attn.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.attn.c_attn.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.attn.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.attn.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.ln_1.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.ln_1.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.ln_2.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.ln_2.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.attn.c_attn.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.attn.c_attn.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.attn.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.attn.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.ln_1.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.ln_1.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.ln_2.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.ln_2.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.attn.c_attn.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.attn.c_attn.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.attn.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.attn.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.ln_1.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.ln_1.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.ln_2.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.ln_2.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.attn.c_attn.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.attn.c_attn.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.attn.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.attn.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.ln_1.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.ln_1.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.ln_2.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.ln_2.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.attn.c_attn.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.attn.c_attn.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.attn.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.attn.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.ln_1.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.ln_1.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.ln_2.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.ln_2.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.attn.c_attn.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.attn.c_attn.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.attn.c_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.attn.c_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.ln_1.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.ln_1.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.ln_2.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.ln_2.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.attn.c_attn.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.attn.c_attn.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.attn.c_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.attn.c_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.ln_1.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.ln_1.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.ln_2.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.ln_2.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.attn.c_attn.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.attn.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.ln_1.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.ln_1.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.ln_2.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.ln_2.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.30.attn.c_attn.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.attn.c_attn.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.attn.c_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.attn.c_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.ln_1.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.ln_1.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.ln_2.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.ln_2.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.attn.c_attn.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.attn.c_attn.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.attn.c_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.attn.c_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.ln_1.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.ln_1.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.ln_2.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.ln_2.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.attn.c_attn.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.attn.c_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.ln_1.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.ln_1.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.ln_2.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.ln_2.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.attn.c_attn.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.attn.c_attn.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.attn.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.attn.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.ln_1.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.ln_1.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.ln_2.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.ln_2.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.attn.c_attn.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.attn.c_attn.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.attn.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.attn.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.ln_1.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.ln_1.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.ln_2.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.ln_2.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.attn.c_attn.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.attn.c_attn.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.attn.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.attn.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.ln_1.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.ln_1.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.ln_2.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.ln_2.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.attn.c_attn.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.attn.c_attn.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.attn.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.attn.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.ln_1.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.ln_1.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.ln_2.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.ln_2.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.attn.c_attn.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.attn.c_attn.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.attn.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.attn.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.ln_1.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.ln_1.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.ln_2.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.ln_2.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"transformer.ln_f.bias": "model-00006-of-00006.safetensors",
|
||||
"transformer.ln_f.weight": "model-00006-of-00006.safetensors",
|
||||
"transformer.wpe.weight": "model-00001-of-00006.safetensors",
|
||||
"transformer.wte.weight": "model-00001-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"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
spiece.model
Normal file
3
spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f4bda2cd84ff0ac659cda40e746c55f47ee3e57cf18471670ad26998c28be52d
|
||||
size 1071955
|
||||
48
tokenizer_config.json
Normal file
48
tokenizer_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"do_lower_case": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"keep_accents": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<pad>",
|
||||
"remove_space": false,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "GPTSw3Tokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user