KnutJaegersberg/black_goo_recipe_b
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: KnutJaegersberg/black_goo_recipe_b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-09 07:15:41 +08:00
commit b5faee4cce
12 changed files with 1600 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

46
README.md Normal file
View File

@@ -0,0 +1,46 @@
---
license: cc-by-nc-4.0
---
Prompt Example:
```
### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### Instruction:
How do you fine tune a large language model?
### Response:
To fine-tune a large language model, we use various techniques to improve its performance and adjust its parameters based on user feedback. These techniques include:
1. Fine tuning the original model with additional data. For example, adding more training examples or using specialized datasets such as question answering or natural language inference tasks. This helps the model learn new concepts and skills by interacting with additional information sources.
2. Using transfer learning methods to incorporate knowledge from other models that have been pre-trained for specific domains. For instance, using pre-trained embeddings from neural networks trained on text classification tasks like sentiment analysis or question answering to help fine-tuning the main language model.
3. Improving the quality of the training data. We may optimize the training process by increasing the accuracy of provided data sets (e.g., by improving word embedding quality), refining the selection of relevant examples, and/or providing additional supervision signals during training.
4. Incorporating knowledge from external resources such as domain-specific lexicons or domain-specific knowledge bases. For example, incorporating domain-specific rules and facts into the model to help it understand domain-specific terminology and semantics.
5. Employing techniques like dropout regularization and dropout sampling to avoid overfitting and reduce overconfidence in the model's predictions.
6. Utilizing meta-learning methods such as reinforcement learning or self-supervised learning to enable the model to adapt quickly to changing situations without being explicitly programmed.
7. Incorporating human input through crowdsourcing or user testing to validate the model's performance and ensure user satisfaction.
8. Implementing various optimization strategies to improve efficiency and reduce computational costs while maintaining high performance levels.
In conclusion, fine tuning a large language model requires combining various techniques including fine tuning, transfer learning, improved data quality, external resources, meta-learning, optimization strategies, crowd sourcing, and user testing. These approaches aim to improve the model's ability to handle various tasks and provide users with better experiences in their daily interactions with language systems.
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__black_goo_recipe_b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 33.72 |
| ARC (25-shot) | 37.63 |
| HellaSwag (10-shot) | 66.72 |
| MMLU (5-shot) | 25.68 |
| TruthfulQA (0-shot) | 37.09 |
| Winogrande (5-shot) | 63.77 |
| GSM8K (5-shot) | 0.08 |
| DROP (3-shot) | 5.1 |

35
config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"_name_or_path": "/run/media/knut/HD/huggingface models/language models/llama-alternatives/LLongMA-3b/",
"architectures": [
"LlamaForCausalLM"
],
"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": 3200,
"initializer_range": 0.02,
"intermediate_size": 8640,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.32.0.dev0",
"use_cache": true,
"vocab_size": 32000
}

152
configuration_llama.py Normal file
View File

@@ -0,0 +1,152 @@
# 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.
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 three 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,
hidden_act="silu",
max_position_embeddings=2048,
initializer_range=0.02,
rms_norm_eps=1e-6,
use_cache=True,
pad_token_id=0,
bos_token_id=1,
eos_token_id=2,
tie_word_embeddings=False,
rope_scaling=None,
**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
self.hidden_act = hidden_act
self.initializer_range = initializer_range
self.rms_norm_eps = rms_norm_eps
self.use_cache = use_cache
self.rope_scaling = rope_scaling
self._rope_scaling_validation()
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", "ntk"]:
raise ValueError(
f"`rope_scaling`'s name field must be one of ['linear', 'dynamic', 'ntk'], 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": "4.32.0.dev0"
}

1016
modeling_llama.py Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model-00001-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:318b3c4e4232361f65be3279e9c71a460c9e4fc348d4e3f7193c73d22200961b
size 9990691091

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9f28d5d338e25ffd8a630b1c02dd74761de451a0ab7217ccab1ac0a250665c4
size 3715284377

244
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,244 @@
{
"metadata": {
"total_size": 13705894400
},
"weight_map": {
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"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:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
size 534194

33
tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 8192,
"pad_token": null,
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}