WhiteRabbitNeo/Trinity-13B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: WhiteRabbitNeo/Trinity-13B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-26 09:34:16 +08:00
commit 7f3e5bbd86
17 changed files with 1965 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Trinity.png filter=lfs diff=lfs merge=lfs -text

180
README.md Normal file
View File

@@ -0,0 +1,180 @@
---
license: llama2
---
# Trinity
![Trinity](https://huggingface.co/migtissera/Trinity-13B-v1.0/resolve/main/Trinity.png)
Trinity is a coding specific model series that can be used to create autonomous agents. In the future, we will be releasing agent software that uses this model.
# Our Offensive Cybersecurity Model WhiteRabbitNeo-33B model is now in beta!
Check out the Prompt Enhancing feature! Access at: https://www.whiterabbitneo.com/
# Join Our Discord Server
Join us at: https://discord.gg/8Ynkrcbk92 (Updated on Dec 29th. Now permanent link to join)
# Terms of Use
By accessing and using this Artificial Intelligence (AI) model, you, the user, acknowledge and agree that you are solely responsible for your use of the model and its outcomes. You hereby agree to indemnify, defend, and hold harmless the creators, developers, and any affiliated persons or entities of this AI model from and against any and all claims, liabilities, damages, losses, costs, expenses, fees (including reasonable attorneys' fees and court costs) that may arise, directly or indirectly, from your use of the AI model.
This AI model is provided "as is" and "as available" without any warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and non-infringement. The creators make no warranty that the AI model will meet your requirements or be available on an uninterrupted, secure, or error-free basis.
Your use of the AI model is at your own risk and discretion, and you will be solely responsible for any damage to computer systems or loss of data that results from the use of the AI model.
This disclaimer constitutes part of the agreement between you and the creators of the AI model regarding your use of the model, superseding any prior agreements between you and the creators regarding your use of this AI model.
# Sample Inference Code
```
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "/home/migel/models/WhiteRabbitNeo"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_4bit=False,
load_in_8bit=True,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.5,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
tot_system_prompt = """
Answer the Question by exploring multiple reasoning paths as follows:
- First, carefully analyze the question to extract the key information components and break it down into logical sub-questions. This helps set up the framework for reasoning. The goal is to construct an internal search tree.
- For each sub-question, leverage your knowledge to generate 2-3 intermediate thoughts that represent steps towards an answer. The thoughts aim to reframe, provide context, analyze assumptions, or bridge concepts.
- Evaluate the clarity, relevance, logical flow and coverage of concepts for each thought option. Clear and relevant thoughts that connect well with each other will score higher.
- Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.
- If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.
- Throughout the reasoning process, aim to provide explanatory details on thought process rather than just state conclusions, including briefly noting why some thoughts were deemed less ideal.
- Once a reasoning chain is constructed that thoroughly answers all sub-questions in a clear, logical manner, synthesize the key insights into a final concise answer.
- Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.
In summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.
"""
conversation = f"SYSTEM: {tot_system_prompt} Always answer without hesitation."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
# print(conversation)
json_data = {"prompt": user_input, "answer": answer}
# print(json_data)
# with open(output_file_path, "a") as output_file:
# output_file.write(json.dumps(json_data) + "\n")
```
# Sample Conversation:
You: Code me a Fast API server, with one endpoint. This endpoint returns files from a S3 bucket.
Here is how to code a Fast API server with one endpoint that returns files from an S3 bucket:
```python
from fastapi import FastAPI
from starlette.responses import StreamingResponse
import boto3
import botocore.exceptions
app = FastAPI()
s3_client = boto3.client('s3')
@app.get("/s3files")
async def get_s3_files(bucket_name: str, key: str):
try:
obj = s3_client.get_object(Bucket=bucket_name, Key=key)
return StreamingResponse(obj['Body'], media_type=obj['ContentType'])
except botocore.exceptions.ClientError as e:
return {"error": str(e)}, 404
```
To explain:
- We initialize a FastAPI app and an S3 client
- The `/s3files` endpoint takes the bucket name and object key as parameters
- We try to get the object from S3 using the S3 client
- If successful, we return the object's Body wrapped in a StreamingResponse, setting the ContentType
- If the client raises an error, we return a 404 with the error message
This allows clients to request files from an S3 bucket by specifying the bucket name and object key. The endpoint streams the file content back to the client.
To elaborate further:
- The endpoint can be extended to validate inputs, handle authentication, logging, etc.
- We could make this endpoint more generic by accepting a list of object keys instead of requiring a single key.
- There are several ways to optimize performance, like caching responses.
Let me know if you have any other questions!
You: How do I authenticate s3?
Here are a few ways to authenticate with S3:
1. Credentials - You can provide AWS access key ID and secret access key to boto3. This will sign requests automatically.
```python
import boto3
s3 = boto3.client('s3',
aws_access_key_id='YOUR_ACCESS_KEY',
aws_secret_access_key='YOUR_SECRET_KEY')
```
2. IAM roles - If you are running on EC2 with an IAM role, you don't need to provide credentials. Boto3 will automatically use the role.
3. Environment variables - Store credentials in environment variables and read them in boto3.
4. AWS credentials file - Store credentials in ~/.aws/credentials. Boto3 will automatically use them.
5. STS Assume roles - Get temporary credentials from STS and assume a role to access S3.
6. AWS SDK credential providers - Use environment variables, configuration files, etc to load credentials.
So in summary, the best way depends on your deployment environment. The best practice is to use IAM roles when possible. Other options like environment variables and credential files can be useful for testing.
Let me know if you have any other questions!

3
Trinity.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d737b133f13fe8e647e16a13c810e86d098cf345fc01aad8e075af7b67d96799
size 1000924

35
config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"_name_or_path": "/home/migel/CodeLlama-13B-fp16",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_llama.LlamaConfig",
"AutoModel": "modeling_llama.LlamaModel",
"AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM",
"AutoModelForSequenceClassification": "modeling_llama.LlamaForSequenceClassification"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"use_cache": false,
"vocab_size": 32016
}

176
configuration_llama.py Normal file
View File

@@ -0,0 +1,176 @@
# coding=utf-8
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
#
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
# and OPT implementations in this library. It has been modified from its
# original forms to accommodate minor architectural differences compared
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" LLaMA model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
class LlamaConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`LlamaModel`]. It is used to instantiate an LLaMA
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
defaults will yield a similar configuration to that of the LLaMA-7B.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
vocab_size (`int`, *optional*, defaults to 32000):
Vocabulary size of the LLaMA model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`LlamaModel`]
hidden_size (`int`, *optional*, defaults to 4096):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to 11008):
Dimension of the MLP representations.
num_hidden_layers (`int`, *optional*, defaults to 32):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 32):
Number of attention heads for each attention layer in the Transformer encoder.
num_key_value_heads (`int`, *optional*):
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
by meanpooling all the original heads within that group. For more details checkout [this
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
`num_attention_heads`.
pretraining_tp (`int`, *optional*, defaults to `1`):
Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
issue](https://github.com/pytorch/pytorch/issues/76232).
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
The non-linear activation function (function or string) in the decoder.
max_position_embeddings (`int`, *optional*, defaults to 2048):
The maximum sequence length that this model might ever be used with. Typically set this to something large
just in case (e.g., 512 or 1024 or 2048).
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
rms_norm_eps (`float`, *optional*, defaults to 1e-12):
The epsilon used by the rms normalization layers.
use_cache (`bool`, *optional*, defaults to `True`):
Whether or not the model should return the last key/values attentions (not used by all models). Only
relevant if `config.is_decoder=True`.
tie_word_embeddings(`bool`, *optional*, defaults to `False`):
Whether to tie weight embeddings
rope_scaling (`Dict`, *optional*):
Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
strategies: linear and dynamic. Their scaling factor must be an float greater than 1. The expected format
is `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
`max_position_embeddings` to the expected new maximum. See the following thread for more information on how
these scaling strategies behave:
https://www.reddit.com/r/LocalLLaMA/comments/14mrgpr/dynamically_scaled_rope_further_increases/. This is an
experimental feature, subject to breaking API changes in future versions.
Example:
```python
>>> from transformers import LlamaModel, LlamaConfig
>>> # Initializing a LLaMA llama-7b style configuration
>>> configuration = LlamaConfig()
>>> # Initializing a model from the llama-7b style configuration
>>> model = LlamaModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "llama"
keys_to_ignore_at_inference = ["past_key_values"]
def __init__(
self,
vocab_size=32000,
hidden_size=4096,
intermediate_size=11008,
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=None,
hidden_act="silu",
max_position_embeddings=2048,
initializer_range=0.02,
rms_norm_eps=1e-6,
use_cache=True,
pad_token_id=None,
bos_token_id=1,
eos_token_id=2,
pretraining_tp=1,
tie_word_embeddings=False,
rope_scaling=None,
rope_theta=10000,
**kwargs,
):
self.vocab_size = vocab_size
self.max_position_embeddings = max_position_embeddings
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
# for backward compatibility
if num_key_value_heads is None:
num_key_value_heads = num_attention_heads
self.num_key_value_heads = num_key_value_heads
self.hidden_act = hidden_act
self.initializer_range = initializer_range
self.rms_norm_eps = rms_norm_eps
self.pretraining_tp = pretraining_tp
self.use_cache = use_cache
self.rope_scaling = rope_scaling
self._rope_scaling_validation()
self.rope_theta = rope_theta
super().__init__(
pad_token_id=pad_token_id,
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
tie_word_embeddings=tie_word_embeddings,
**kwargs,
)
def _rope_scaling_validation(self):
"""
Validate the `rope_scaling` configuration.
"""
if self.rope_scaling is None:
return
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
raise ValueError(
"`rope_scaling` must be a dictionary with with two fields, `name` and `factor`, "
f"got {self.rope_scaling}"
)
rope_scaling_type = self.rope_scaling.get("type", None)
rope_scaling_factor = self.rope_scaling.get("factor", None)
if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
raise ValueError(
f"`rope_scaling`'s name field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
)
if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
raise ValueError(f"`rope_scaling`'s factor field must be an float > 1, got {rope_scaling_factor}")

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.36.2"
}

1020
modeling_llama.py Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model-00001-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4fb84b117c225f68594ea57afc94a2c342dd9ce9fff8dc97e246785c94e0999
size 4978445615

3
pytorch_model-00002-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b024698f2a9c69e8be83aa18217aa86facd906aede0ea5f6f32662e87079b87
size 4970438651

3
pytorch_model-00003-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8cafb26bb5ade9d5a97226c92c3cad9da901e4e548fb1b5187711a7406a77130
size 4970438651

3
pytorch_model-00004-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3968029dfbc9093633a5a1b3e2418fa114a7f96dba3aa4dc1ace14822dfd9a84
size 4933717697

3
pytorch_model-00005-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1666c691ed4343fd030c2f48e77ec43614aed391ab94df77b2c102f9132ee488
size 4933738845

3
pytorch_model-00006-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a401a8909558a649814833c84bdcbd2c705ca0db716c4c5cbca29f2757ed9f8b
size 1245404445

370
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,370 @@
{
"metadata": {
"total_size": 26032056320
},
"weight_map": {
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.norm.weight": "pytorch_model-00006-of-00006.bin"
}
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"additional_special_tokens": [
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
size 500058

87
tokenizer_config.json Normal file
View File

@@ -0,0 +1,87 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"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
},
"32007": {
"content": "▁<PRE>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "▁<SUF>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "▁<MID>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "▁<EOT>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eot_token": "▁<EOT>",
"fill_token": "<FILL_ME>",
"legacy": null,
"middle_token": "▁<MID>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"prefix_token": "▁<PRE>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"suffix_first": false,
"suffix_token": "▁<SUF>",
"tokenizer_class": "CodeLlamaTokenizer",
"trust_remote_code": false,
"unk_token": "<unk>",
"use_default_system_prompt": true,
"use_fast": true
}