Hello
Browse files- README.md +267 -3
- config.json +39 -0
- generation_config.json +7 -0
- gitattributes +35 -0
- model.safetensors.index.json +635 -0
- output-00001-of-00002.safetensors +3 -0
- output-00002-of-00002.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +188 -0
README.md
CHANGED
|
@@ -1,3 +1,267 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
base_model: ibm-granite/granite-20b-code-base
|
| 4 |
+
inference: true
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
datasets:
|
| 7 |
+
- bigcode/commitpackft
|
| 8 |
+
- TIGER-Lab/MathInstruct
|
| 9 |
+
- meta-math/MetaMathQA
|
| 10 |
+
- glaiveai/glaive-code-assistant-v3
|
| 11 |
+
- glaive-function-calling-v2
|
| 12 |
+
- bugdaryan/sql-create-context-instruction
|
| 13 |
+
- garage-bAInd/Open-Platypus
|
| 14 |
+
- nvidia/HelpSteer
|
| 15 |
+
metrics:
|
| 16 |
+
- code_eval
|
| 17 |
+
library_name: transformers
|
| 18 |
+
tags:
|
| 19 |
+
- code
|
| 20 |
+
model-index:
|
| 21 |
+
- name: granite-20b-code-instruct
|
| 22 |
+
results:
|
| 23 |
+
- task:
|
| 24 |
+
type: text-generation
|
| 25 |
+
dataset:
|
| 26 |
+
type: bigcode/humanevalpack
|
| 27 |
+
name: HumanEvalSynthesis(Python)
|
| 28 |
+
metrics:
|
| 29 |
+
- name: pass@1
|
| 30 |
+
type: pass@1
|
| 31 |
+
value: 60.4
|
| 32 |
+
veriefied: false
|
| 33 |
+
- task:
|
| 34 |
+
type: text-generation
|
| 35 |
+
dataset:
|
| 36 |
+
type: bigcode/humanevalpack
|
| 37 |
+
name: HumanEvalSynthesis(JavaScript)
|
| 38 |
+
metrics:
|
| 39 |
+
- name: pass@1
|
| 40 |
+
type: pass@1
|
| 41 |
+
value: 53.7
|
| 42 |
+
veriefied: false
|
| 43 |
+
- task:
|
| 44 |
+
type: text-generation
|
| 45 |
+
dataset:
|
| 46 |
+
type: bigcode/humanevalpack
|
| 47 |
+
name: HumanEvalSynthesis(Java)
|
| 48 |
+
metrics:
|
| 49 |
+
- name: pass@1
|
| 50 |
+
type: pass@1
|
| 51 |
+
value: 58.5
|
| 52 |
+
veriefied: false
|
| 53 |
+
- task:
|
| 54 |
+
type: text-generation
|
| 55 |
+
dataset:
|
| 56 |
+
type: bigcode/humanevalpack
|
| 57 |
+
name: HumanEvalSynthesis(Go)
|
| 58 |
+
metrics:
|
| 59 |
+
- name: pass@1
|
| 60 |
+
type: pass@1
|
| 61 |
+
value: 42.1
|
| 62 |
+
veriefied: false
|
| 63 |
+
- task:
|
| 64 |
+
type: text-generation
|
| 65 |
+
dataset:
|
| 66 |
+
type: bigcode/humanevalpack
|
| 67 |
+
name: HumanEvalSynthesis(C++)
|
| 68 |
+
metrics:
|
| 69 |
+
- name: pass@1
|
| 70 |
+
type: pass@1
|
| 71 |
+
value: 45.7
|
| 72 |
+
veriefied: false
|
| 73 |
+
- task:
|
| 74 |
+
type: text-generation
|
| 75 |
+
dataset:
|
| 76 |
+
type: bigcode/humanevalpack
|
| 77 |
+
name: HumanEvalSynthesis(Rust)
|
| 78 |
+
metrics:
|
| 79 |
+
- name: pass@1
|
| 80 |
+
type: pass@1
|
| 81 |
+
value: 42.7
|
| 82 |
+
veriefied: false
|
| 83 |
+
- task:
|
| 84 |
+
type: text-generation
|
| 85 |
+
dataset:
|
| 86 |
+
type: bigcode/humanevalpack
|
| 87 |
+
name: HumanEvalExplain(Python)
|
| 88 |
+
metrics:
|
| 89 |
+
- name: pass@1
|
| 90 |
+
type: pass@1
|
| 91 |
+
value: 44.5
|
| 92 |
+
veriefied: false
|
| 93 |
+
- task:
|
| 94 |
+
type: text-generation
|
| 95 |
+
dataset:
|
| 96 |
+
type: bigcode/humanevalpack
|
| 97 |
+
name: HumanEvalExplain(JavaScript)
|
| 98 |
+
metrics:
|
| 99 |
+
- name: pass@1
|
| 100 |
+
type: pass@1
|
| 101 |
+
value: 42.7
|
| 102 |
+
veriefied: false
|
| 103 |
+
- task:
|
| 104 |
+
type: text-generation
|
| 105 |
+
dataset:
|
| 106 |
+
type: bigcode/humanevalpack
|
| 107 |
+
name: HumanEvalExplain(Java)
|
| 108 |
+
metrics:
|
| 109 |
+
- name: pass@1
|
| 110 |
+
type: pass@1
|
| 111 |
+
value: 49.4
|
| 112 |
+
veriefied: false
|
| 113 |
+
- task:
|
| 114 |
+
type: text-generation
|
| 115 |
+
dataset:
|
| 116 |
+
type: bigcode/humanevalpack
|
| 117 |
+
name: HumanEvalExplain(Go)
|
| 118 |
+
metrics:
|
| 119 |
+
- name: pass@1
|
| 120 |
+
type: pass@1
|
| 121 |
+
value: 32.3
|
| 122 |
+
veriefied: false
|
| 123 |
+
- task:
|
| 124 |
+
type: text-generation
|
| 125 |
+
dataset:
|
| 126 |
+
type: bigcode/humanevalpack
|
| 127 |
+
name: HumanEvalExplain(C++)
|
| 128 |
+
metrics:
|
| 129 |
+
- name: pass@1
|
| 130 |
+
type: pass@1
|
| 131 |
+
value: 42.1
|
| 132 |
+
veriefied: false
|
| 133 |
+
- task:
|
| 134 |
+
type: text-generation
|
| 135 |
+
dataset:
|
| 136 |
+
type: bigcode/humanevalpack
|
| 137 |
+
name: HumanEvalExplain(Rust)
|
| 138 |
+
metrics:
|
| 139 |
+
- name: pass@1
|
| 140 |
+
type: pass@1
|
| 141 |
+
value: 18.3
|
| 142 |
+
veriefied: false
|
| 143 |
+
- task:
|
| 144 |
+
type: text-generation
|
| 145 |
+
dataset:
|
| 146 |
+
type: bigcode/humanevalpack
|
| 147 |
+
name: HumanEvalFix(Python)
|
| 148 |
+
metrics:
|
| 149 |
+
- name: pass@1
|
| 150 |
+
type: pass@1
|
| 151 |
+
value: 43.9
|
| 152 |
+
veriefied: false
|
| 153 |
+
- task:
|
| 154 |
+
type: text-generation
|
| 155 |
+
dataset:
|
| 156 |
+
type: bigcode/humanevalpack
|
| 157 |
+
name: HumanEvalFix(JavaScript)
|
| 158 |
+
metrics:
|
| 159 |
+
- name: pass@1
|
| 160 |
+
type: pass@1
|
| 161 |
+
value: 43.9
|
| 162 |
+
veriefied: false
|
| 163 |
+
- task:
|
| 164 |
+
type: text-generation
|
| 165 |
+
dataset:
|
| 166 |
+
type: bigcode/humanevalpack
|
| 167 |
+
name: HumanEvalFix(Java)
|
| 168 |
+
metrics:
|
| 169 |
+
- name: pass@1
|
| 170 |
+
type: pass@1
|
| 171 |
+
value: 45.7
|
| 172 |
+
veriefied: false
|
| 173 |
+
- task:
|
| 174 |
+
type: text-generation
|
| 175 |
+
dataset:
|
| 176 |
+
type: bigcode/humanevalpack
|
| 177 |
+
name: HumanEvalFix(Go)
|
| 178 |
+
metrics:
|
| 179 |
+
- name: pass@1
|
| 180 |
+
type: pass@1
|
| 181 |
+
value: 41.5
|
| 182 |
+
veriefied: false
|
| 183 |
+
- task:
|
| 184 |
+
type: text-generation
|
| 185 |
+
dataset:
|
| 186 |
+
type: bigcode/humanevalpack
|
| 187 |
+
name: HumanEvalFix(C++)
|
| 188 |
+
metrics:
|
| 189 |
+
- name: pass@1
|
| 190 |
+
type: pass@1
|
| 191 |
+
value: 41.5
|
| 192 |
+
veriefied: false
|
| 193 |
+
- task:
|
| 194 |
+
type: text-generation
|
| 195 |
+
dataset:
|
| 196 |
+
type: bigcode/humanevalpack
|
| 197 |
+
name: HumanEvalFix(Rust)
|
| 198 |
+
metrics:
|
| 199 |
+
- name: pass@1
|
| 200 |
+
type: pass@1
|
| 201 |
+
value: 29.9
|
| 202 |
+
veriefied: false
|
| 203 |
+
---
|
| 204 |
+
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
# Granite-20B-Code-Instruct
|
| 208 |
+
|
| 209 |
+
## Model Summary
|
| 210 |
+
**Granite-20B-Code-Instruct** is a 20B parameter model fine tuned from *Granite-20B-Code-Base* on a combination of **permissively licensed** instruction data to enhance instruction following capabilities including logical reasoning and problem-solving skills.
|
| 211 |
+
|
| 212 |
+
- **Developers:** IBM Research
|
| 213 |
+
- **GitHub Repository:** [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models)
|
| 214 |
+
- **Paper:** [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://github.com/ibm-granite/granite-code-models/blob/main/paper.pdf)
|
| 215 |
+
- **Release Date**: May 6th, 2024
|
| 216 |
+
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).
|
| 217 |
+
|
| 218 |
+
## Usage
|
| 219 |
+
### Intended use
|
| 220 |
+
The model is designed to respond to coding related instructions and can be used to build coding assitants.
|
| 221 |
+
|
| 222 |
+
<!-- TO DO: Check starcoder2 instruct code example that includes the template https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1 -->
|
| 223 |
+
|
| 224 |
+
### Generation
|
| 225 |
+
This is a simple example of how to use **Granite-20B-Code-Instruct** model.
|
| 226 |
+
|
| 227 |
+
```python
|
| 228 |
+
import torch
|
| 229 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 230 |
+
device = "cuda" # or "cpu"
|
| 231 |
+
model_path = "ibm-granite/granite-20b-code-instruct"
|
| 232 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 233 |
+
# drop device_map if running on CPU
|
| 234 |
+
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
|
| 235 |
+
model.eval()
|
| 236 |
+
# change input text as desired
|
| 237 |
+
chat = [
|
| 238 |
+
{ "role": "user", "content": "Write a code to find the maximum value in a list of numbers." },
|
| 239 |
+
]
|
| 240 |
+
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
|
| 241 |
+
# tokenize the text
|
| 242 |
+
input_tokens = tokenizer(chat, return_tensors="pt")
|
| 243 |
+
# transfer tokenized inputs to the device
|
| 244 |
+
for i in input_tokens:
|
| 245 |
+
input_tokens[i] = input_tokens[i].to(device)
|
| 246 |
+
# generate output tokens
|
| 247 |
+
output = model.generate(**input_tokens, max_new_tokens=100)
|
| 248 |
+
# decode output tokens into text
|
| 249 |
+
output = tokenizer.batch_decode(output)
|
| 250 |
+
# loop over the batch to print, in this example the batch size is 1
|
| 251 |
+
for i in output:
|
| 252 |
+
print(i)
|
| 253 |
+
```
|
| 254 |
+
|
| 255 |
+
<!-- TO DO: Check this part -->
|
| 256 |
+
## Training Data
|
| 257 |
+
Granite Code Instruct models are trained on the following types of data.
|
| 258 |
+
* Code Commits Datasets: we sourced code commits data from the [CommitPackFT](https://huggingface.co/datasets/bigcode/commitpackft) dataset, a filtered version of the full CommitPack dataset. From CommitPackFT dataset, we only consider data for 92 programming languages. Our inclusion criteria boils down to selecting programming languages common across CommitPackFT and the 116 languages that we considered to pretrain the code-base model (*Granite-20B-Code-Base*).
|
| 259 |
+
* Math Datasets: We consider two high-quality math datasets, [MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct) and [MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA). Due to license issues, we filtered out GSM8K-RFT and Camel-Math from MathInstruct dataset.
|
| 260 |
+
* Code Instruction Datasets: We use [Glaive-Code-Assistant-v3](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v3), [Glaive-Function-Calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2), [NL2SQL11](https://huggingface.co/datasets/bugdaryan/sql-create-context-instruction) and a small collection of synthetic API calling datasets.
|
| 261 |
+
* Language Instruction Datasets: We include high-quality datasets such as [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer) and an open license-filtered version of [Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). We also include a collection of hardcoded prompts to ensure our model generates correct outputs given inquiries about its name or developers.
|
| 262 |
+
|
| 263 |
+
## Infrastructure
|
| 264 |
+
We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs.
|
| 265 |
+
|
| 266 |
+
## Ethical Considerations and Limitations
|
| 267 |
+
Granite code instruct models are primarily finetuned using instruction-response pairs across a specific set of programming languages. Thus, their performance may be limited with out-of-domain programming languages. In this situation, it is beneficial providing few-shot examples to steer the model's output. Moreover, developers should perform safety testing and target-specific tuning before deploying these models on critical applications. The model also inherits ethical considerations and limitations from its base model. For more information, please refer to *[Granite-20B-Code-Base](https://huggingface.co/ibm-granite/granite-20b-code-base)* model card.
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_pytorch_tanh",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTBigCodeForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_softmax_in_fp32": true,
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt_bigcode",
|
| 14 |
+
"multi_query": true,
|
| 15 |
+
"n_embd": 6144,
|
| 16 |
+
"n_head": 48,
|
| 17 |
+
"n_inner": 24576,
|
| 18 |
+
"n_layer": 52,
|
| 19 |
+
"n_positions": 8192,
|
| 20 |
+
"pad_token_id": 4,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attention_softmax_in_fp32": true,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.41.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 49152,
|
| 28 |
+
"quantization_config": {
|
| 29 |
+
"quant_method": "exl2",
|
| 30 |
+
"version": "0.0.20",
|
| 31 |
+
"bits": 4.0,
|
| 32 |
+
"head_bits": 6,
|
| 33 |
+
"calibration": {
|
| 34 |
+
"rows": 100,
|
| 35 |
+
"length": 2048,
|
| 36 |
+
"dataset": "(default)"
|
| 37 |
+
}
|
| 38 |
+
}
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"pad_token_id": 4,
|
| 6 |
+
"transformers_version": "4.41.0.dev0"
|
| 7 |
+
}
|
gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,635 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 40133986304
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
| 7 |
+
"transformer.h.0.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
| 8 |
+
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 9 |
+
"transformer.h.0.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 10 |
+
"transformer.h.0.ln_1.bias": "model-00001-of-00009.safetensors",
|
| 11 |
+
"transformer.h.0.ln_1.weight": "model-00001-of-00009.safetensors",
|
| 12 |
+
"transformer.h.0.ln_2.bias": "model-00001-of-00009.safetensors",
|
| 13 |
+
"transformer.h.0.ln_2.weight": "model-00001-of-00009.safetensors",
|
| 14 |
+
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
| 15 |
+
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
| 16 |
+
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 17 |
+
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 18 |
+
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
| 19 |
+
"transformer.h.1.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
| 20 |
+
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 21 |
+
"transformer.h.1.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 22 |
+
"transformer.h.1.ln_1.bias": "model-00001-of-00009.safetensors",
|
| 23 |
+
"transformer.h.1.ln_1.weight": "model-00001-of-00009.safetensors",
|
| 24 |
+
"transformer.h.1.ln_2.bias": "model-00001-of-00009.safetensors",
|
| 25 |
+
"transformer.h.1.ln_2.weight": "model-00001-of-00009.safetensors",
|
| 26 |
+
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
| 27 |
+
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
| 28 |
+
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 29 |
+
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 30 |
+
"transformer.h.10.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
| 31 |
+
"transformer.h.10.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
| 32 |
+
"transformer.h.10.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 33 |
+
"transformer.h.10.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 34 |
+
"transformer.h.10.ln_1.bias": "model-00002-of-00009.safetensors",
|
| 35 |
+
"transformer.h.10.ln_1.weight": "model-00002-of-00009.safetensors",
|
| 36 |
+
"transformer.h.10.ln_2.bias": "model-00002-of-00009.safetensors",
|
| 37 |
+
"transformer.h.10.ln_2.weight": "model-00002-of-00009.safetensors",
|
| 38 |
+
"transformer.h.10.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
| 39 |
+
"transformer.h.10.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
| 40 |
+
"transformer.h.10.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 41 |
+
"transformer.h.10.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 42 |
+
"transformer.h.11.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
| 43 |
+
"transformer.h.11.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
| 44 |
+
"transformer.h.11.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 45 |
+
"transformer.h.11.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 46 |
+
"transformer.h.11.ln_1.bias": "model-00002-of-00009.safetensors",
|
| 47 |
+
"transformer.h.11.ln_1.weight": "model-00002-of-00009.safetensors",
|
| 48 |
+
"transformer.h.11.ln_2.bias": "model-00002-of-00009.safetensors",
|
| 49 |
+
"transformer.h.11.ln_2.weight": "model-00002-of-00009.safetensors",
|
| 50 |
+
"transformer.h.11.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
| 51 |
+
"transformer.h.11.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
| 52 |
+
"transformer.h.11.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 53 |
+
"transformer.h.11.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 54 |
+
"transformer.h.12.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
| 55 |
+
"transformer.h.12.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
| 56 |
+
"transformer.h.12.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 57 |
+
"transformer.h.12.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 58 |
+
"transformer.h.12.ln_1.bias": "model-00002-of-00009.safetensors",
|
| 59 |
+
"transformer.h.12.ln_1.weight": "model-00002-of-00009.safetensors",
|
| 60 |
+
"transformer.h.12.ln_2.bias": "model-00003-of-00009.safetensors",
|
| 61 |
+
"transformer.h.12.ln_2.weight": "model-00003-of-00009.safetensors",
|
| 62 |
+
"transformer.h.12.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
| 63 |
+
"transformer.h.12.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
| 64 |
+
"transformer.h.12.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 65 |
+
"transformer.h.12.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 66 |
+
"transformer.h.13.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
| 67 |
+
"transformer.h.13.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
| 68 |
+
"transformer.h.13.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 69 |
+
"transformer.h.13.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 70 |
+
"transformer.h.13.ln_1.bias": "model-00003-of-00009.safetensors",
|
| 71 |
+
"transformer.h.13.ln_1.weight": "model-00003-of-00009.safetensors",
|
| 72 |
+
"transformer.h.13.ln_2.bias": "model-00003-of-00009.safetensors",
|
| 73 |
+
"transformer.h.13.ln_2.weight": "model-00003-of-00009.safetensors",
|
| 74 |
+
"transformer.h.13.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
| 75 |
+
"transformer.h.13.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
| 76 |
+
"transformer.h.13.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 77 |
+
"transformer.h.13.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 78 |
+
"transformer.h.14.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
| 79 |
+
"transformer.h.14.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
| 80 |
+
"transformer.h.14.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 81 |
+
"transformer.h.14.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 82 |
+
"transformer.h.14.ln_1.bias": "model-00003-of-00009.safetensors",
|
| 83 |
+
"transformer.h.14.ln_1.weight": "model-00003-of-00009.safetensors",
|
| 84 |
+
"transformer.h.14.ln_2.bias": "model-00003-of-00009.safetensors",
|
| 85 |
+
"transformer.h.14.ln_2.weight": "model-00003-of-00009.safetensors",
|
| 86 |
+
"transformer.h.14.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
| 87 |
+
"transformer.h.14.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
| 88 |
+
"transformer.h.14.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 89 |
+
"transformer.h.14.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 90 |
+
"transformer.h.15.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
| 91 |
+
"transformer.h.15.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
| 92 |
+
"transformer.h.15.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 93 |
+
"transformer.h.15.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 94 |
+
"transformer.h.15.ln_1.bias": "model-00003-of-00009.safetensors",
|
| 95 |
+
"transformer.h.15.ln_1.weight": "model-00003-of-00009.safetensors",
|
| 96 |
+
"transformer.h.15.ln_2.bias": "model-00003-of-00009.safetensors",
|
| 97 |
+
"transformer.h.15.ln_2.weight": "model-00003-of-00009.safetensors",
|
| 98 |
+
"transformer.h.15.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
| 99 |
+
"transformer.h.15.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
| 100 |
+
"transformer.h.15.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 101 |
+
"transformer.h.15.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 102 |
+
"transformer.h.16.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
| 103 |
+
"transformer.h.16.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
| 104 |
+
"transformer.h.16.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 105 |
+
"transformer.h.16.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 106 |
+
"transformer.h.16.ln_1.bias": "model-00003-of-00009.safetensors",
|
| 107 |
+
"transformer.h.16.ln_1.weight": "model-00003-of-00009.safetensors",
|
| 108 |
+
"transformer.h.16.ln_2.bias": "model-00003-of-00009.safetensors",
|
| 109 |
+
"transformer.h.16.ln_2.weight": "model-00003-of-00009.safetensors",
|
| 110 |
+
"transformer.h.16.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
| 111 |
+
"transformer.h.16.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
| 112 |
+
"transformer.h.16.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 113 |
+
"transformer.h.16.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 114 |
+
"transformer.h.17.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
| 115 |
+
"transformer.h.17.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
| 116 |
+
"transformer.h.17.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 117 |
+
"transformer.h.17.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 118 |
+
"transformer.h.17.ln_1.bias": "model-00003-of-00009.safetensors",
|
| 119 |
+
"transformer.h.17.ln_1.weight": "model-00003-of-00009.safetensors",
|
| 120 |
+
"transformer.h.17.ln_2.bias": "model-00003-of-00009.safetensors",
|
| 121 |
+
"transformer.h.17.ln_2.weight": "model-00003-of-00009.safetensors",
|
| 122 |
+
"transformer.h.17.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
| 123 |
+
"transformer.h.17.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
| 124 |
+
"transformer.h.17.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 125 |
+
"transformer.h.17.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 126 |
+
"transformer.h.18.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
| 127 |
+
"transformer.h.18.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
| 128 |
+
"transformer.h.18.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
| 129 |
+
"transformer.h.18.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
| 130 |
+
"transformer.h.18.ln_1.bias": "model-00003-of-00009.safetensors",
|
| 131 |
+
"transformer.h.18.ln_1.weight": "model-00003-of-00009.safetensors",
|
| 132 |
+
"transformer.h.18.ln_2.bias": "model-00003-of-00009.safetensors",
|
| 133 |
+
"transformer.h.18.ln_2.weight": "model-00003-of-00009.safetensors",
|
| 134 |
+
"transformer.h.18.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
| 135 |
+
"transformer.h.18.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
| 136 |
+
"transformer.h.18.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 137 |
+
"transformer.h.18.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 138 |
+
"transformer.h.19.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
| 139 |
+
"transformer.h.19.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
| 140 |
+
"transformer.h.19.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 141 |
+
"transformer.h.19.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 142 |
+
"transformer.h.19.ln_1.bias": "model-00004-of-00009.safetensors",
|
| 143 |
+
"transformer.h.19.ln_1.weight": "model-00004-of-00009.safetensors",
|
| 144 |
+
"transformer.h.19.ln_2.bias": "model-00004-of-00009.safetensors",
|
| 145 |
+
"transformer.h.19.ln_2.weight": "model-00004-of-00009.safetensors",
|
| 146 |
+
"transformer.h.19.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
| 147 |
+
"transformer.h.19.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
| 148 |
+
"transformer.h.19.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 149 |
+
"transformer.h.19.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 150 |
+
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
| 151 |
+
"transformer.h.2.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
| 152 |
+
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 153 |
+
"transformer.h.2.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 154 |
+
"transformer.h.2.ln_1.bias": "model-00001-of-00009.safetensors",
|
| 155 |
+
"transformer.h.2.ln_1.weight": "model-00001-of-00009.safetensors",
|
| 156 |
+
"transformer.h.2.ln_2.bias": "model-00001-of-00009.safetensors",
|
| 157 |
+
"transformer.h.2.ln_2.weight": "model-00001-of-00009.safetensors",
|
| 158 |
+
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
| 159 |
+
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
| 160 |
+
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 161 |
+
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 162 |
+
"transformer.h.20.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
| 163 |
+
"transformer.h.20.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
| 164 |
+
"transformer.h.20.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 165 |
+
"transformer.h.20.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 166 |
+
"transformer.h.20.ln_1.bias": "model-00004-of-00009.safetensors",
|
| 167 |
+
"transformer.h.20.ln_1.weight": "model-00004-of-00009.safetensors",
|
| 168 |
+
"transformer.h.20.ln_2.bias": "model-00004-of-00009.safetensors",
|
| 169 |
+
"transformer.h.20.ln_2.weight": "model-00004-of-00009.safetensors",
|
| 170 |
+
"transformer.h.20.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
| 171 |
+
"transformer.h.20.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
| 172 |
+
"transformer.h.20.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 173 |
+
"transformer.h.20.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 174 |
+
"transformer.h.21.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
| 175 |
+
"transformer.h.21.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
| 176 |
+
"transformer.h.21.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 177 |
+
"transformer.h.21.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 178 |
+
"transformer.h.21.ln_1.bias": "model-00004-of-00009.safetensors",
|
| 179 |
+
"transformer.h.21.ln_1.weight": "model-00004-of-00009.safetensors",
|
| 180 |
+
"transformer.h.21.ln_2.bias": "model-00004-of-00009.safetensors",
|
| 181 |
+
"transformer.h.21.ln_2.weight": "model-00004-of-00009.safetensors",
|
| 182 |
+
"transformer.h.21.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
| 183 |
+
"transformer.h.21.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
| 184 |
+
"transformer.h.21.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 185 |
+
"transformer.h.21.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 186 |
+
"transformer.h.22.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
| 187 |
+
"transformer.h.22.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
| 188 |
+
"transformer.h.22.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 189 |
+
"transformer.h.22.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 190 |
+
"transformer.h.22.ln_1.bias": "model-00004-of-00009.safetensors",
|
| 191 |
+
"transformer.h.22.ln_1.weight": "model-00004-of-00009.safetensors",
|
| 192 |
+
"transformer.h.22.ln_2.bias": "model-00004-of-00009.safetensors",
|
| 193 |
+
"transformer.h.22.ln_2.weight": "model-00004-of-00009.safetensors",
|
| 194 |
+
"transformer.h.22.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
| 195 |
+
"transformer.h.22.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
| 196 |
+
"transformer.h.22.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 197 |
+
"transformer.h.22.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 198 |
+
"transformer.h.23.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
| 199 |
+
"transformer.h.23.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
| 200 |
+
"transformer.h.23.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 201 |
+
"transformer.h.23.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 202 |
+
"transformer.h.23.ln_1.bias": "model-00004-of-00009.safetensors",
|
| 203 |
+
"transformer.h.23.ln_1.weight": "model-00004-of-00009.safetensors",
|
| 204 |
+
"transformer.h.23.ln_2.bias": "model-00004-of-00009.safetensors",
|
| 205 |
+
"transformer.h.23.ln_2.weight": "model-00004-of-00009.safetensors",
|
| 206 |
+
"transformer.h.23.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
| 207 |
+
"transformer.h.23.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
| 208 |
+
"transformer.h.23.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 209 |
+
"transformer.h.23.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 210 |
+
"transformer.h.24.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
| 211 |
+
"transformer.h.24.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
| 212 |
+
"transformer.h.24.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 213 |
+
"transformer.h.24.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 214 |
+
"transformer.h.24.ln_1.bias": "model-00004-of-00009.safetensors",
|
| 215 |
+
"transformer.h.24.ln_1.weight": "model-00004-of-00009.safetensors",
|
| 216 |
+
"transformer.h.24.ln_2.bias": "model-00004-of-00009.safetensors",
|
| 217 |
+
"transformer.h.24.ln_2.weight": "model-00004-of-00009.safetensors",
|
| 218 |
+
"transformer.h.24.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
| 219 |
+
"transformer.h.24.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
| 220 |
+
"transformer.h.24.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
| 221 |
+
"transformer.h.24.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
| 222 |
+
"transformer.h.25.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
| 223 |
+
"transformer.h.25.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
| 224 |
+
"transformer.h.25.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 225 |
+
"transformer.h.25.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 226 |
+
"transformer.h.25.ln_1.bias": "model-00004-of-00009.safetensors",
|
| 227 |
+
"transformer.h.25.ln_1.weight": "model-00004-of-00009.safetensors",
|
| 228 |
+
"transformer.h.25.ln_2.bias": "model-00005-of-00009.safetensors",
|
| 229 |
+
"transformer.h.25.ln_2.weight": "model-00005-of-00009.safetensors",
|
| 230 |
+
"transformer.h.25.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
| 231 |
+
"transformer.h.25.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
| 232 |
+
"transformer.h.25.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 233 |
+
"transformer.h.25.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 234 |
+
"transformer.h.26.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
| 235 |
+
"transformer.h.26.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
| 236 |
+
"transformer.h.26.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 237 |
+
"transformer.h.26.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 238 |
+
"transformer.h.26.ln_1.bias": "model-00005-of-00009.safetensors",
|
| 239 |
+
"transformer.h.26.ln_1.weight": "model-00005-of-00009.safetensors",
|
| 240 |
+
"transformer.h.26.ln_2.bias": "model-00005-of-00009.safetensors",
|
| 241 |
+
"transformer.h.26.ln_2.weight": "model-00005-of-00009.safetensors",
|
| 242 |
+
"transformer.h.26.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
| 243 |
+
"transformer.h.26.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
| 244 |
+
"transformer.h.26.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 245 |
+
"transformer.h.26.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 246 |
+
"transformer.h.27.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
| 247 |
+
"transformer.h.27.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
| 248 |
+
"transformer.h.27.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 249 |
+
"transformer.h.27.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 250 |
+
"transformer.h.27.ln_1.bias": "model-00005-of-00009.safetensors",
|
| 251 |
+
"transformer.h.27.ln_1.weight": "model-00005-of-00009.safetensors",
|
| 252 |
+
"transformer.h.27.ln_2.bias": "model-00005-of-00009.safetensors",
|
| 253 |
+
"transformer.h.27.ln_2.weight": "model-00005-of-00009.safetensors",
|
| 254 |
+
"transformer.h.27.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
| 255 |
+
"transformer.h.27.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
| 256 |
+
"transformer.h.27.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 257 |
+
"transformer.h.27.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 258 |
+
"transformer.h.28.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
| 259 |
+
"transformer.h.28.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
| 260 |
+
"transformer.h.28.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 261 |
+
"transformer.h.28.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 262 |
+
"transformer.h.28.ln_1.bias": "model-00005-of-00009.safetensors",
|
| 263 |
+
"transformer.h.28.ln_1.weight": "model-00005-of-00009.safetensors",
|
| 264 |
+
"transformer.h.28.ln_2.bias": "model-00005-of-00009.safetensors",
|
| 265 |
+
"transformer.h.28.ln_2.weight": "model-00005-of-00009.safetensors",
|
| 266 |
+
"transformer.h.28.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
| 267 |
+
"transformer.h.28.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
| 268 |
+
"transformer.h.28.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 269 |
+
"transformer.h.28.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 270 |
+
"transformer.h.29.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
| 271 |
+
"transformer.h.29.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
| 272 |
+
"transformer.h.29.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 273 |
+
"transformer.h.29.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 274 |
+
"transformer.h.29.ln_1.bias": "model-00005-of-00009.safetensors",
|
| 275 |
+
"transformer.h.29.ln_1.weight": "model-00005-of-00009.safetensors",
|
| 276 |
+
"transformer.h.29.ln_2.bias": "model-00005-of-00009.safetensors",
|
| 277 |
+
"transformer.h.29.ln_2.weight": "model-00005-of-00009.safetensors",
|
| 278 |
+
"transformer.h.29.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
| 279 |
+
"transformer.h.29.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
| 280 |
+
"transformer.h.29.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 281 |
+
"transformer.h.29.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 282 |
+
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
| 283 |
+
"transformer.h.3.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
| 284 |
+
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 285 |
+
"transformer.h.3.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 286 |
+
"transformer.h.3.ln_1.bias": "model-00001-of-00009.safetensors",
|
| 287 |
+
"transformer.h.3.ln_1.weight": "model-00001-of-00009.safetensors",
|
| 288 |
+
"transformer.h.3.ln_2.bias": "model-00001-of-00009.safetensors",
|
| 289 |
+
"transformer.h.3.ln_2.weight": "model-00001-of-00009.safetensors",
|
| 290 |
+
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
| 291 |
+
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
| 292 |
+
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 293 |
+
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 294 |
+
"transformer.h.30.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
| 295 |
+
"transformer.h.30.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
| 296 |
+
"transformer.h.30.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 297 |
+
"transformer.h.30.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 298 |
+
"transformer.h.30.ln_1.bias": "model-00005-of-00009.safetensors",
|
| 299 |
+
"transformer.h.30.ln_1.weight": "model-00005-of-00009.safetensors",
|
| 300 |
+
"transformer.h.30.ln_2.bias": "model-00005-of-00009.safetensors",
|
| 301 |
+
"transformer.h.30.ln_2.weight": "model-00005-of-00009.safetensors",
|
| 302 |
+
"transformer.h.30.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
| 303 |
+
"transformer.h.30.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
| 304 |
+
"transformer.h.30.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 305 |
+
"transformer.h.30.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 306 |
+
"transformer.h.31.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
| 307 |
+
"transformer.h.31.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
| 308 |
+
"transformer.h.31.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
| 309 |
+
"transformer.h.31.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
| 310 |
+
"transformer.h.31.ln_1.bias": "model-00005-of-00009.safetensors",
|
| 311 |
+
"transformer.h.31.ln_1.weight": "model-00005-of-00009.safetensors",
|
| 312 |
+
"transformer.h.31.ln_2.bias": "model-00005-of-00009.safetensors",
|
| 313 |
+
"transformer.h.31.ln_2.weight": "model-00005-of-00009.safetensors",
|
| 314 |
+
"transformer.h.31.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
| 315 |
+
"transformer.h.31.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
| 316 |
+
"transformer.h.31.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 317 |
+
"transformer.h.31.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 318 |
+
"transformer.h.32.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
| 319 |
+
"transformer.h.32.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
| 320 |
+
"transformer.h.32.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 321 |
+
"transformer.h.32.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 322 |
+
"transformer.h.32.ln_1.bias": "model-00006-of-00009.safetensors",
|
| 323 |
+
"transformer.h.32.ln_1.weight": "model-00006-of-00009.safetensors",
|
| 324 |
+
"transformer.h.32.ln_2.bias": "model-00006-of-00009.safetensors",
|
| 325 |
+
"transformer.h.32.ln_2.weight": "model-00006-of-00009.safetensors",
|
| 326 |
+
"transformer.h.32.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
| 327 |
+
"transformer.h.32.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
| 328 |
+
"transformer.h.32.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 329 |
+
"transformer.h.32.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 330 |
+
"transformer.h.33.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
| 331 |
+
"transformer.h.33.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
| 332 |
+
"transformer.h.33.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 333 |
+
"transformer.h.33.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 334 |
+
"transformer.h.33.ln_1.bias": "model-00006-of-00009.safetensors",
|
| 335 |
+
"transformer.h.33.ln_1.weight": "model-00006-of-00009.safetensors",
|
| 336 |
+
"transformer.h.33.ln_2.bias": "model-00006-of-00009.safetensors",
|
| 337 |
+
"transformer.h.33.ln_2.weight": "model-00006-of-00009.safetensors",
|
| 338 |
+
"transformer.h.33.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
| 339 |
+
"transformer.h.33.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
| 340 |
+
"transformer.h.33.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 341 |
+
"transformer.h.33.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 342 |
+
"transformer.h.34.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
| 343 |
+
"transformer.h.34.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
| 344 |
+
"transformer.h.34.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 345 |
+
"transformer.h.34.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 346 |
+
"transformer.h.34.ln_1.bias": "model-00006-of-00009.safetensors",
|
| 347 |
+
"transformer.h.34.ln_1.weight": "model-00006-of-00009.safetensors",
|
| 348 |
+
"transformer.h.34.ln_2.bias": "model-00006-of-00009.safetensors",
|
| 349 |
+
"transformer.h.34.ln_2.weight": "model-00006-of-00009.safetensors",
|
| 350 |
+
"transformer.h.34.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
| 351 |
+
"transformer.h.34.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
| 352 |
+
"transformer.h.34.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 353 |
+
"transformer.h.34.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 354 |
+
"transformer.h.35.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
| 355 |
+
"transformer.h.35.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
| 356 |
+
"transformer.h.35.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 357 |
+
"transformer.h.35.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 358 |
+
"transformer.h.35.ln_1.bias": "model-00006-of-00009.safetensors",
|
| 359 |
+
"transformer.h.35.ln_1.weight": "model-00006-of-00009.safetensors",
|
| 360 |
+
"transformer.h.35.ln_2.bias": "model-00006-of-00009.safetensors",
|
| 361 |
+
"transformer.h.35.ln_2.weight": "model-00006-of-00009.safetensors",
|
| 362 |
+
"transformer.h.35.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
| 363 |
+
"transformer.h.35.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
| 364 |
+
"transformer.h.35.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 365 |
+
"transformer.h.35.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 366 |
+
"transformer.h.36.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
| 367 |
+
"transformer.h.36.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
| 368 |
+
"transformer.h.36.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 369 |
+
"transformer.h.36.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 370 |
+
"transformer.h.36.ln_1.bias": "model-00006-of-00009.safetensors",
|
| 371 |
+
"transformer.h.36.ln_1.weight": "model-00006-of-00009.safetensors",
|
| 372 |
+
"transformer.h.36.ln_2.bias": "model-00006-of-00009.safetensors",
|
| 373 |
+
"transformer.h.36.ln_2.weight": "model-00006-of-00009.safetensors",
|
| 374 |
+
"transformer.h.36.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
| 375 |
+
"transformer.h.36.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
| 376 |
+
"transformer.h.36.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 377 |
+
"transformer.h.36.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 378 |
+
"transformer.h.37.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
| 379 |
+
"transformer.h.37.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
| 380 |
+
"transformer.h.37.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 381 |
+
"transformer.h.37.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 382 |
+
"transformer.h.37.ln_1.bias": "model-00006-of-00009.safetensors",
|
| 383 |
+
"transformer.h.37.ln_1.weight": "model-00006-of-00009.safetensors",
|
| 384 |
+
"transformer.h.37.ln_2.bias": "model-00006-of-00009.safetensors",
|
| 385 |
+
"transformer.h.37.ln_2.weight": "model-00006-of-00009.safetensors",
|
| 386 |
+
"transformer.h.37.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
| 387 |
+
"transformer.h.37.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
| 388 |
+
"transformer.h.37.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
| 389 |
+
"transformer.h.37.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
| 390 |
+
"transformer.h.38.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
| 391 |
+
"transformer.h.38.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
| 392 |
+
"transformer.h.38.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 393 |
+
"transformer.h.38.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 394 |
+
"transformer.h.38.ln_1.bias": "model-00006-of-00009.safetensors",
|
| 395 |
+
"transformer.h.38.ln_1.weight": "model-00006-of-00009.safetensors",
|
| 396 |
+
"transformer.h.38.ln_2.bias": "model-00007-of-00009.safetensors",
|
| 397 |
+
"transformer.h.38.ln_2.weight": "model-00007-of-00009.safetensors",
|
| 398 |
+
"transformer.h.38.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
| 399 |
+
"transformer.h.38.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
| 400 |
+
"transformer.h.38.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 401 |
+
"transformer.h.38.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 402 |
+
"transformer.h.39.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
| 403 |
+
"transformer.h.39.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
| 404 |
+
"transformer.h.39.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 405 |
+
"transformer.h.39.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 406 |
+
"transformer.h.39.ln_1.bias": "model-00007-of-00009.safetensors",
|
| 407 |
+
"transformer.h.39.ln_1.weight": "model-00007-of-00009.safetensors",
|
| 408 |
+
"transformer.h.39.ln_2.bias": "model-00007-of-00009.safetensors",
|
| 409 |
+
"transformer.h.39.ln_2.weight": "model-00007-of-00009.safetensors",
|
| 410 |
+
"transformer.h.39.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
| 411 |
+
"transformer.h.39.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
| 412 |
+
"transformer.h.39.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 413 |
+
"transformer.h.39.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 414 |
+
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
| 415 |
+
"transformer.h.4.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
| 416 |
+
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 417 |
+
"transformer.h.4.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 418 |
+
"transformer.h.4.ln_1.bias": "model-00001-of-00009.safetensors",
|
| 419 |
+
"transformer.h.4.ln_1.weight": "model-00001-of-00009.safetensors",
|
| 420 |
+
"transformer.h.4.ln_2.bias": "model-00001-of-00009.safetensors",
|
| 421 |
+
"transformer.h.4.ln_2.weight": "model-00001-of-00009.safetensors",
|
| 422 |
+
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
| 423 |
+
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
| 424 |
+
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 425 |
+
"transformer.h.4.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 426 |
+
"transformer.h.40.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
| 427 |
+
"transformer.h.40.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
| 428 |
+
"transformer.h.40.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 429 |
+
"transformer.h.40.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 430 |
+
"transformer.h.40.ln_1.bias": "model-00007-of-00009.safetensors",
|
| 431 |
+
"transformer.h.40.ln_1.weight": "model-00007-of-00009.safetensors",
|
| 432 |
+
"transformer.h.40.ln_2.bias": "model-00007-of-00009.safetensors",
|
| 433 |
+
"transformer.h.40.ln_2.weight": "model-00007-of-00009.safetensors",
|
| 434 |
+
"transformer.h.40.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
| 435 |
+
"transformer.h.40.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
| 436 |
+
"transformer.h.40.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 437 |
+
"transformer.h.40.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 438 |
+
"transformer.h.41.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
| 439 |
+
"transformer.h.41.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
| 440 |
+
"transformer.h.41.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 441 |
+
"transformer.h.41.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 442 |
+
"transformer.h.41.ln_1.bias": "model-00007-of-00009.safetensors",
|
| 443 |
+
"transformer.h.41.ln_1.weight": "model-00007-of-00009.safetensors",
|
| 444 |
+
"transformer.h.41.ln_2.bias": "model-00007-of-00009.safetensors",
|
| 445 |
+
"transformer.h.41.ln_2.weight": "model-00007-of-00009.safetensors",
|
| 446 |
+
"transformer.h.41.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
| 447 |
+
"transformer.h.41.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
| 448 |
+
"transformer.h.41.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 449 |
+
"transformer.h.41.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 450 |
+
"transformer.h.42.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
| 451 |
+
"transformer.h.42.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
| 452 |
+
"transformer.h.42.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 453 |
+
"transformer.h.42.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 454 |
+
"transformer.h.42.ln_1.bias": "model-00007-of-00009.safetensors",
|
| 455 |
+
"transformer.h.42.ln_1.weight": "model-00007-of-00009.safetensors",
|
| 456 |
+
"transformer.h.42.ln_2.bias": "model-00007-of-00009.safetensors",
|
| 457 |
+
"transformer.h.42.ln_2.weight": "model-00007-of-00009.safetensors",
|
| 458 |
+
"transformer.h.42.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
| 459 |
+
"transformer.h.42.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
| 460 |
+
"transformer.h.42.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 461 |
+
"transformer.h.42.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 462 |
+
"transformer.h.43.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
| 463 |
+
"transformer.h.43.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
| 464 |
+
"transformer.h.43.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 465 |
+
"transformer.h.43.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 466 |
+
"transformer.h.43.ln_1.bias": "model-00007-of-00009.safetensors",
|
| 467 |
+
"transformer.h.43.ln_1.weight": "model-00007-of-00009.safetensors",
|
| 468 |
+
"transformer.h.43.ln_2.bias": "model-00007-of-00009.safetensors",
|
| 469 |
+
"transformer.h.43.ln_2.weight": "model-00007-of-00009.safetensors",
|
| 470 |
+
"transformer.h.43.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
| 471 |
+
"transformer.h.43.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
| 472 |
+
"transformer.h.43.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 473 |
+
"transformer.h.43.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 474 |
+
"transformer.h.44.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
| 475 |
+
"transformer.h.44.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
| 476 |
+
"transformer.h.44.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
| 477 |
+
"transformer.h.44.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
| 478 |
+
"transformer.h.44.ln_1.bias": "model-00007-of-00009.safetensors",
|
| 479 |
+
"transformer.h.44.ln_1.weight": "model-00007-of-00009.safetensors",
|
| 480 |
+
"transformer.h.44.ln_2.bias": "model-00007-of-00009.safetensors",
|
| 481 |
+
"transformer.h.44.ln_2.weight": "model-00007-of-00009.safetensors",
|
| 482 |
+
"transformer.h.44.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
| 483 |
+
"transformer.h.44.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
| 484 |
+
"transformer.h.44.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 485 |
+
"transformer.h.44.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 486 |
+
"transformer.h.45.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
| 487 |
+
"transformer.h.45.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
| 488 |
+
"transformer.h.45.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 489 |
+
"transformer.h.45.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 490 |
+
"transformer.h.45.ln_1.bias": "model-00008-of-00009.safetensors",
|
| 491 |
+
"transformer.h.45.ln_1.weight": "model-00008-of-00009.safetensors",
|
| 492 |
+
"transformer.h.45.ln_2.bias": "model-00008-of-00009.safetensors",
|
| 493 |
+
"transformer.h.45.ln_2.weight": "model-00008-of-00009.safetensors",
|
| 494 |
+
"transformer.h.45.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
| 495 |
+
"transformer.h.45.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
| 496 |
+
"transformer.h.45.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 497 |
+
"transformer.h.45.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 498 |
+
"transformer.h.46.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
| 499 |
+
"transformer.h.46.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
| 500 |
+
"transformer.h.46.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 501 |
+
"transformer.h.46.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 502 |
+
"transformer.h.46.ln_1.bias": "model-00008-of-00009.safetensors",
|
| 503 |
+
"transformer.h.46.ln_1.weight": "model-00008-of-00009.safetensors",
|
| 504 |
+
"transformer.h.46.ln_2.bias": "model-00008-of-00009.safetensors",
|
| 505 |
+
"transformer.h.46.ln_2.weight": "model-00008-of-00009.safetensors",
|
| 506 |
+
"transformer.h.46.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
| 507 |
+
"transformer.h.46.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
| 508 |
+
"transformer.h.46.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 509 |
+
"transformer.h.46.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 510 |
+
"transformer.h.47.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
| 511 |
+
"transformer.h.47.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
| 512 |
+
"transformer.h.47.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 513 |
+
"transformer.h.47.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 514 |
+
"transformer.h.47.ln_1.bias": "model-00008-of-00009.safetensors",
|
| 515 |
+
"transformer.h.47.ln_1.weight": "model-00008-of-00009.safetensors",
|
| 516 |
+
"transformer.h.47.ln_2.bias": "model-00008-of-00009.safetensors",
|
| 517 |
+
"transformer.h.47.ln_2.weight": "model-00008-of-00009.safetensors",
|
| 518 |
+
"transformer.h.47.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
| 519 |
+
"transformer.h.47.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
| 520 |
+
"transformer.h.47.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 521 |
+
"transformer.h.47.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 522 |
+
"transformer.h.48.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
| 523 |
+
"transformer.h.48.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
| 524 |
+
"transformer.h.48.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 525 |
+
"transformer.h.48.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 526 |
+
"transformer.h.48.ln_1.bias": "model-00008-of-00009.safetensors",
|
| 527 |
+
"transformer.h.48.ln_1.weight": "model-00008-of-00009.safetensors",
|
| 528 |
+
"transformer.h.48.ln_2.bias": "model-00008-of-00009.safetensors",
|
| 529 |
+
"transformer.h.48.ln_2.weight": "model-00008-of-00009.safetensors",
|
| 530 |
+
"transformer.h.48.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
| 531 |
+
"transformer.h.48.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
| 532 |
+
"transformer.h.48.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 533 |
+
"transformer.h.48.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 534 |
+
"transformer.h.49.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
| 535 |
+
"transformer.h.49.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
| 536 |
+
"transformer.h.49.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 537 |
+
"transformer.h.49.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 538 |
+
"transformer.h.49.ln_1.bias": "model-00008-of-00009.safetensors",
|
| 539 |
+
"transformer.h.49.ln_1.weight": "model-00008-of-00009.safetensors",
|
| 540 |
+
"transformer.h.49.ln_2.bias": "model-00008-of-00009.safetensors",
|
| 541 |
+
"transformer.h.49.ln_2.weight": "model-00008-of-00009.safetensors",
|
| 542 |
+
"transformer.h.49.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
| 543 |
+
"transformer.h.49.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
| 544 |
+
"transformer.h.49.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 545 |
+
"transformer.h.49.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 546 |
+
"transformer.h.5.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
| 547 |
+
"transformer.h.5.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
| 548 |
+
"transformer.h.5.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
| 549 |
+
"transformer.h.5.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
| 550 |
+
"transformer.h.5.ln_1.bias": "model-00001-of-00009.safetensors",
|
| 551 |
+
"transformer.h.5.ln_1.weight": "model-00001-of-00009.safetensors",
|
| 552 |
+
"transformer.h.5.ln_2.bias": "model-00001-of-00009.safetensors",
|
| 553 |
+
"transformer.h.5.ln_2.weight": "model-00001-of-00009.safetensors",
|
| 554 |
+
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
| 555 |
+
"transformer.h.5.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
| 556 |
+
"transformer.h.5.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 557 |
+
"transformer.h.5.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 558 |
+
"transformer.h.50.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
| 559 |
+
"transformer.h.50.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
| 560 |
+
"transformer.h.50.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 561 |
+
"transformer.h.50.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 562 |
+
"transformer.h.50.ln_1.bias": "model-00008-of-00009.safetensors",
|
| 563 |
+
"transformer.h.50.ln_1.weight": "model-00008-of-00009.safetensors",
|
| 564 |
+
"transformer.h.50.ln_2.bias": "model-00008-of-00009.safetensors",
|
| 565 |
+
"transformer.h.50.ln_2.weight": "model-00008-of-00009.safetensors",
|
| 566 |
+
"transformer.h.50.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
| 567 |
+
"transformer.h.50.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
| 568 |
+
"transformer.h.50.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
| 569 |
+
"transformer.h.50.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
| 570 |
+
"transformer.h.51.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
| 571 |
+
"transformer.h.51.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
| 572 |
+
"transformer.h.51.attn.c_proj.bias": "model-00009-of-00009.safetensors",
|
| 573 |
+
"transformer.h.51.attn.c_proj.weight": "model-00009-of-00009.safetensors",
|
| 574 |
+
"transformer.h.51.ln_1.bias": "model-00008-of-00009.safetensors",
|
| 575 |
+
"transformer.h.51.ln_1.weight": "model-00008-of-00009.safetensors",
|
| 576 |
+
"transformer.h.51.ln_2.bias": "model-00009-of-00009.safetensors",
|
| 577 |
+
"transformer.h.51.ln_2.weight": "model-00009-of-00009.safetensors",
|
| 578 |
+
"transformer.h.51.mlp.c_fc.bias": "model-00009-of-00009.safetensors",
|
| 579 |
+
"transformer.h.51.mlp.c_fc.weight": "model-00009-of-00009.safetensors",
|
| 580 |
+
"transformer.h.51.mlp.c_proj.bias": "model-00009-of-00009.safetensors",
|
| 581 |
+
"transformer.h.51.mlp.c_proj.weight": "model-00009-of-00009.safetensors",
|
| 582 |
+
"transformer.h.6.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
| 583 |
+
"transformer.h.6.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
| 584 |
+
"transformer.h.6.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 585 |
+
"transformer.h.6.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 586 |
+
"transformer.h.6.ln_1.bias": "model-00002-of-00009.safetensors",
|
| 587 |
+
"transformer.h.6.ln_1.weight": "model-00002-of-00009.safetensors",
|
| 588 |
+
"transformer.h.6.ln_2.bias": "model-00002-of-00009.safetensors",
|
| 589 |
+
"transformer.h.6.ln_2.weight": "model-00002-of-00009.safetensors",
|
| 590 |
+
"transformer.h.6.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
| 591 |
+
"transformer.h.6.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
| 592 |
+
"transformer.h.6.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 593 |
+
"transformer.h.6.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 594 |
+
"transformer.h.7.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
| 595 |
+
"transformer.h.7.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
| 596 |
+
"transformer.h.7.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 597 |
+
"transformer.h.7.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 598 |
+
"transformer.h.7.ln_1.bias": "model-00002-of-00009.safetensors",
|
| 599 |
+
"transformer.h.7.ln_1.weight": "model-00002-of-00009.safetensors",
|
| 600 |
+
"transformer.h.7.ln_2.bias": "model-00002-of-00009.safetensors",
|
| 601 |
+
"transformer.h.7.ln_2.weight": "model-00002-of-00009.safetensors",
|
| 602 |
+
"transformer.h.7.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
| 603 |
+
"transformer.h.7.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
| 604 |
+
"transformer.h.7.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 605 |
+
"transformer.h.7.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 606 |
+
"transformer.h.8.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
| 607 |
+
"transformer.h.8.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
| 608 |
+
"transformer.h.8.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 609 |
+
"transformer.h.8.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 610 |
+
"transformer.h.8.ln_1.bias": "model-00002-of-00009.safetensors",
|
| 611 |
+
"transformer.h.8.ln_1.weight": "model-00002-of-00009.safetensors",
|
| 612 |
+
"transformer.h.8.ln_2.bias": "model-00002-of-00009.safetensors",
|
| 613 |
+
"transformer.h.8.ln_2.weight": "model-00002-of-00009.safetensors",
|
| 614 |
+
"transformer.h.8.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
| 615 |
+
"transformer.h.8.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
| 616 |
+
"transformer.h.8.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 617 |
+
"transformer.h.8.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 618 |
+
"transformer.h.9.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
| 619 |
+
"transformer.h.9.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
| 620 |
+
"transformer.h.9.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 621 |
+
"transformer.h.9.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 622 |
+
"transformer.h.9.ln_1.bias": "model-00002-of-00009.safetensors",
|
| 623 |
+
"transformer.h.9.ln_1.weight": "model-00002-of-00009.safetensors",
|
| 624 |
+
"transformer.h.9.ln_2.bias": "model-00002-of-00009.safetensors",
|
| 625 |
+
"transformer.h.9.ln_2.weight": "model-00002-of-00009.safetensors",
|
| 626 |
+
"transformer.h.9.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
| 627 |
+
"transformer.h.9.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
| 628 |
+
"transformer.h.9.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
| 629 |
+
"transformer.h.9.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
| 630 |
+
"transformer.ln_f.bias": "model-00009-of-00009.safetensors",
|
| 631 |
+
"transformer.ln_f.weight": "model-00009-of-00009.safetensors",
|
| 632 |
+
"transformer.wpe.weight": "model-00001-of-00009.safetensors",
|
| 633 |
+
"transformer.wte.weight": "model-00001-of-00009.safetensors"
|
| 634 |
+
}
|
| 635 |
+
}
|
output-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b424c91ebd5c3a837612ca40a3bec9e03b7367acbec1d0fddfcf7c535ee561f2
|
| 3 |
+
size 8512092556
|
output-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2dd101a1e60991faf173025ffee484af926e9b8459955684c515797cfbd3b35
|
| 3 |
+
size 2288378028
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": {
|
| 38 |
+
"content": "<|endoftext|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<|endoftext|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"additional_special_tokens": [
|
| 158 |
+
"<|endoftext|>",
|
| 159 |
+
"<fim_prefix>",
|
| 160 |
+
"<fim_middle>",
|
| 161 |
+
"<fim_suffix>",
|
| 162 |
+
"<fim_pad>",
|
| 163 |
+
"<filename>",
|
| 164 |
+
"<gh_stars>",
|
| 165 |
+
"<issue_start>",
|
| 166 |
+
"<issue_comment>",
|
| 167 |
+
"<issue_closed>",
|
| 168 |
+
"<jupyter_start>",
|
| 169 |
+
"<jupyter_text>",
|
| 170 |
+
"<jupyter_code>",
|
| 171 |
+
"<jupyter_output>",
|
| 172 |
+
"<empty_output>",
|
| 173 |
+
"<commit_before>",
|
| 174 |
+
"<commit_msg>",
|
| 175 |
+
"<commit_after>",
|
| 176 |
+
"<reponame>"
|
| 177 |
+
],
|
| 178 |
+
"bos_token": "<|endoftext|>",
|
| 179 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'Question:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'system' %}\n{{ 'System:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Answer:\n' + message['content'] + '\n\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Answer:\n' }}{% endif %}{% endfor %}",
|
| 180 |
+
"clean_up_tokenization_spaces": true,
|
| 181 |
+
"eos_token": "<|endoftext|>",
|
| 182 |
+
"model_max_length": 8192,
|
| 183 |
+
"pad_token": "<|fim_pad|>",
|
| 184 |
+
"padding_side": "left",
|
| 185 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 186 |
+
"unk_token": "<|endoftext|>",
|
| 187 |
+
"vocab_size": 49152
|
| 188 |
+
}
|