初始化项目，由ModelHub XC社区提供模型
Model: utter-project/EuroLLM-22B-Instruct-2512 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
EuroLLM_Public_Summary.pdf filter=lfs diff=lfs merge=lfs -text
|
||||||
3
EuroLLM_Public_Summary.pdf
Normal file
3
EuroLLM_Public_Summary.pdf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:eacc95d2048b6fcfcff936c16912e93dc557c9ad1cfea655df94776b46d5c8f9
|
||||||
|
size 234034
|
||||||
240
README.md
Normal file
240
README.md
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- de
|
||||||
|
- es
|
||||||
|
- fr
|
||||||
|
- it
|
||||||
|
- pt
|
||||||
|
- pl
|
||||||
|
- nl
|
||||||
|
- tr
|
||||||
|
- sv
|
||||||
|
- cs
|
||||||
|
- el
|
||||||
|
- hu
|
||||||
|
- ro
|
||||||
|
- fi
|
||||||
|
- uk
|
||||||
|
- sl
|
||||||
|
- sk
|
||||||
|
- da
|
||||||
|
- lt
|
||||||
|
- lv
|
||||||
|
- et
|
||||||
|
- bg
|
||||||
|
- 'no'
|
||||||
|
- ca
|
||||||
|
- hr
|
||||||
|
- ga
|
||||||
|
- mt
|
||||||
|
- gl
|
||||||
|
- zh
|
||||||
|
- ru
|
||||||
|
- ko
|
||||||
|
- ja
|
||||||
|
- ar
|
||||||
|
- hi
|
||||||
|
library_name: transformers
|
||||||
|
base_model:
|
||||||
|
- utter-project/EuroLLM-22B-2512
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for EuroLLM-22B-Instruct
|
||||||
|
|
||||||
|
This is the model card for EuroLLM-22B-Instruct. You can also check the pre-trained version: [EuroLLM-22B-2515](https://huggingface.co/utter-project/EuroLLM-22B-2512).
|
||||||
|
|
||||||
|
- **Developed by:** Instituto Superior Técnico - University of Lisbon, Instituto de Telecomunicações, University of Edinburgh, Aveni, Unbabel, University of Paris-Saclay, Artefact Research Center, University of Amsterdam, Naver Labs, Sorbonne Université.
|
||||||
|
- **Funded by:** European Union.
|
||||||
|
- **Model type:** A 22B parameter multilingual transfomer LLM.
|
||||||
|
- **Language(s) (NLP):** Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Irish, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish, Arabic, Catalan, Chinese, Galician, Hindi, Japanese, Korean, Norwegian, Russian, Turkish, and Ukrainian.
|
||||||
|
- **License:** Apache License 2.0.
|
||||||
|
|
||||||
|
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
||||||
|
<details><summary>See axolotl config</summary>
|
||||||
|
|
||||||
|
axolotl version: `0.12.2`
|
||||||
|
```yaml
|
||||||
|
auto_resume_from_checkpoints: true
|
||||||
|
use_tensorboard: true
|
||||||
|
|
||||||
|
base_model: utter-project/EuroLLM-22B-2512
|
||||||
|
model_type: AutoModelForCausalLM
|
||||||
|
tokenizer_type: AutoTokenizer
|
||||||
|
|
||||||
|
load_in_8bit: false
|
||||||
|
load_in_4bit: false
|
||||||
|
strict: false
|
||||||
|
|
||||||
|
dataset_processes: 64
|
||||||
|
datasets:
|
||||||
|
- path: utter-project/EuroBlocks-SFT-2512
|
||||||
|
type: chat_template
|
||||||
|
split: train
|
||||||
|
conversation: chatml
|
||||||
|
field_messages: conversations
|
||||||
|
message_field_role: role
|
||||||
|
message_field_content: content
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
train_on_eos: all
|
||||||
|
|
||||||
|
|
||||||
|
chat_template_jinja: "{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'assistant' %}{% else %}{% set role = message['role'] %}{% endif %}<|im_start|>{{ role }}\n{{ message['content'] | trim }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n'}}{% endif %}"
|
||||||
|
|
||||||
|
output_dir: checkpoints
|
||||||
|
val_set_size: 0
|
||||||
|
|
||||||
|
sequence_len: 32768
|
||||||
|
sample_packing: true
|
||||||
|
pad_to_sequence_len: true
|
||||||
|
|
||||||
|
# sequence_parallel_degree: 4
|
||||||
|
# heads_k_stride: 1
|
||||||
|
# ring_attn_func:
|
||||||
|
|
||||||
|
plugins:
|
||||||
|
- axolotl.integrations.liger.LigerPlugin
|
||||||
|
liger_rope: true
|
||||||
|
liger_rms_norm: true
|
||||||
|
liger_glu_activation: true
|
||||||
|
liger_layer_norm: true
|
||||||
|
liger_fused_linear_cross_entropy: true
|
||||||
|
|
||||||
|
# N_GPUS * GRAD_ACC_STEPS * MICRO_BATCH_SIZE * SEQ_LEN = tokens/step ->
|
||||||
|
# Assuming 32 gpus (32 * 2 * 2 * 32k = 4 096 000 tokens/step)
|
||||||
|
gradient_accumulation_steps: 2
|
||||||
|
micro_batch_size: 2
|
||||||
|
|
||||||
|
eval_batch_size: 1
|
||||||
|
num_epochs: 5
|
||||||
|
optimizer: adamw_torch
|
||||||
|
lr_scheduler: cosine
|
||||||
|
learning_rate: 1e-5
|
||||||
|
|
||||||
|
train_on_inputs: false
|
||||||
|
group_by_length: false
|
||||||
|
bf16: true
|
||||||
|
fp16: false
|
||||||
|
tf32: false
|
||||||
|
|
||||||
|
gradient_checkpointing: true
|
||||||
|
logging_steps: 1
|
||||||
|
flash_attention: true
|
||||||
|
flash_attn_cross_entropy: false
|
||||||
|
flash_attn_rms_norm: false
|
||||||
|
flash_attn_fuse_qkv: false
|
||||||
|
flash_attn_fuse_mlp: false
|
||||||
|
|
||||||
|
warmup_steps: 125
|
||||||
|
eval_sample_packing: False
|
||||||
|
save_steps: 500
|
||||||
|
save_total_limit: 2
|
||||||
|
deepspeed: deepspeed_configs/zero3_bf16.json
|
||||||
|
weight_decay: 0.01
|
||||||
|
|
||||||
|
special_tokens:
|
||||||
|
eos_token: "<|im_end|>"
|
||||||
|
|
||||||
|
```
|
||||||
|
</details><br>
|
||||||
|
|
||||||
|
## Model Details
|
||||||
|
|
||||||
|
The EuroLLM project has the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages as well as some additional relevant languages.
|
||||||
|
EuroLLM-22B is a 22B parameter model trained on 4 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets.
|
||||||
|
EuroLLM-22B-Instruct was further instruction tuned on EuroBlocks, an instruction tuning dataset with focus on general instruction-following and machine translation.
|
||||||
|
|
||||||
|
### Architecture
|
||||||
|
|
||||||
|
EuroLLM uses a standard, dense Transformer architecture withgrouped query attention (GQA), pre-layer normalization with RMSNorm, SwiGLU activations and rotary positional embeddings (RoPE) in every layer. Here is a summary of the model hyper-parameters:
|
||||||
|
| | |
|
||||||
|
|--------------------------------------|----------------------|
|
||||||
|
| Sequence Length | 32,768 |
|
||||||
|
| Number of Layers | 56 |
|
||||||
|
| Embedding Size | 6,144 |
|
||||||
|
| FFN Hidden Size | 16,384 |
|
||||||
|
| Number of Heads | 48 |
|
||||||
|
| Number of KV Heads (GQA) | 8 |
|
||||||
|
| Activation Function | SwiGLU |
|
||||||
|
| Position Encodings | RoPE (\Theta=1,000,000) |
|
||||||
|
| Layer Norm | RMSNorm |
|
||||||
|
| Tied Embeddings | No |
|
||||||
|
| Embedding Parameters | 0.786B |
|
||||||
|
| LM Head Parameters | 0.786B |
|
||||||
|
| Non-embedding Parameters | 21.067B |
|
||||||
|
| Total Parameters | 22.639B |
|
||||||
|
|
||||||
|
### Pre-training
|
||||||
|
|
||||||
|
EuroLLM-22B was trained on approximately 4 trillion tokens, using 400 Nvidia H100 GPUs on the MareNostrum5 supercomputer, thanks to an EuroHPC extreme-scale access grant. The training process was carefully structured into three key phases:
|
||||||
|
|
||||||
|
<ol>
|
||||||
|
<li>Initial Pre-training (3.6 trillion tokens)
|
||||||
|
This phase includes the warm-up and constant learning rate stages, during which the model is trained on a mixture of web data alongside higher quality sources such as parallel data, Wikipedia, Arxiv, books, math, code and Apollo datasets. This balanced mix helps the model build a strong multilingual foundation.</li>
|
||||||
|
|
||||||
|
<li>Annealing (400 billion tokens) During this phase, there is a linear decay of the learning rate and we adjust the data mix to reduce the proportion of web data while increasing the multilingual content and select the highest quality data—by making use of quality filters such as [CometKiwi-22](https://huggingface.co/Unbabel/wmt22-cometkiwi-da) and [EuroFilter](https://huggingface.co/utter-project/EuroFilter-v1). This shift helps the model refine its understanding across diverse languages and domains.</li>
|
||||||
|
|
||||||
|
<li>Annealing to Zero (100 billion tokens) In this final stage, the learning rate decays linearly to zero. In this phase, the data mix was optimized to be of even higher quality, in order to polish the model's performance, and long context data sources were upsampled to increase the model context window to 32k tokens.</li>
|
||||||
|
</ol>
|
||||||
|
|
||||||
|
### Post-training
|
||||||
|
|
||||||
|
During post-training, we adapt EuroLLM to be an instruction-following model capable of handling multi-turn conversations. We start by regenerating the final responses from publicly available datasets using several open models, and keep the best candidate using a reward model. To this data, we add records from other datasets (Nemotron, Hermes-3 and Tulu 3), removing duplicates based on the first prompt. This pipeline shows how EuroLLM can be easily adapted for your use-cases.
|
||||||
|
|
||||||
|
The model excels at translation tasks being capable of translating across all official EU languages, matching or outperforming strong models like Gemma-3-27B, Qwen-3-32B and Apertus-70B. Furthermore, when it comes to general benchmarks, it is the best EU-made fully open model.
|
||||||
|
|
||||||
|
|
||||||
|
## Run the model
|
||||||
|
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model_id = "utter-project/EuroLLM-22B-Instruct-2512"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "system",
|
||||||
|
"content": "You are EuroLLM --- an AI assistant specialized in European languages that provides safe, educational and helpful answers.",
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"role": "user", "content": "What is the capital of Portugal? How would you describe it?"
|
||||||
|
},
|
||||||
|
]
|
||||||
|
|
||||||
|
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
|
||||||
|
outputs = model.generate(inputs, max_new_tokens=1024)
|
||||||
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||||
|
|
||||||
|
## Results
|
||||||
|
|
||||||
|
### Multilingual
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
**Table 1:** Comparison of fully open and open-weight LLMs on a suite of multilingual benchmarks, averaging over all languages supported by EuroLLM-22B that are present in each benchmark. The table reports scores on HellaSwag, MMLU, MMLU-Pro, ARC-Challenge, MGSM, FLORES, and WMT24++. The Borda Count (Colombo et al., 2022) reflects the average ranking of each model across all benchmarks. <b>Bold</b> values indicate the best overall system for each benchmark, while <u>underscored</u> values denote the best fully open system.
|
||||||
|
|
||||||
|
### English
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
**Table 2:** Comparison of fully open and open-weight LLMs on a suite of English benchmarks. The table reports scores on IFEval, HellaSwag, MMLU, MMLU-Pro, BBH, ARC-Challenge, GPQA, GSM8K, MATH-500, and HumanEval. The Borda Count reflects the average ranking of each model across all benchmarks. <b>Bold</b> values indicate the best overall system for each benchmark, while <u>underscored</u> values denote the best fully open system.
|
||||||
|
|
||||||
|
## Bias, Risks, and Limitations
|
||||||
|
|
||||||
|
EuroLLM-22B has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
If you use our work, please cite:
|
||||||
|
```
|
||||||
|
@misc{ramos2026eurollm22btechnicalreport,
|
||||||
|
title={EuroLLM-22B: Technical Report},
|
||||||
|
author={Miguel Moura Ramos and Duarte M. Alves and Hippolyte Gisserot-Boukhlef and João Alves and Pedro Henrique Martins and Patrick Fernandes and José Pombal and Nuno M. Guerreiro and Ricardo Rei and Nicolas Boizard and Amin Farajian and Mateusz Klimaszewski and José G. C. de Souza and Barry Haddow and François Yvon and Pierre Colombo and Alexandra Birch and André F. T. Martins},
|
||||||
|
year={2026},
|
||||||
|
eprint={2602.05879},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL},
|
||||||
|
url={https://arxiv.org/abs/2602.05879},
|
||||||
|
}
|
||||||
|
```
|
||||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 4,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 6144,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 16384,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 48,
|
||||||
|
"num_hidden_layers": 54,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.51.3",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 128000
|
||||||
|
}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 3,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": 4,
|
||||||
|
"transformers_version": "4.51.3"
|
||||||
|
}
|
||||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3a69899a3f66414fac96f3ccc1b8daf46372ead956ffb9f65d78f7173f10eb33
|
||||||
|
size 4869690024
|
||||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a25a9a14f0f49ea060651a00bfbd4bc90431d2fbc200768946052f43377360c8
|
||||||
|
size 4882323696
|
||||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ce50ffabcb159e1703817db2229331ea83ef063ef2e62f3d515e45c40253c238
|
||||||
|
size 4882323744
|
||||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f7f6323135f01ecdb736ef388b3528078c38396e8ef6bb3a3e54f40a6acaf388
|
||||||
|
size 4983012192
|
||||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9a48a12955a4f88b2302769fe6c6e55a034404f8a75dd0e6f95db0192b452048
|
||||||
|
size 4957821336
|
||||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e0254ead2f79aaa8a94fd79f4c2825aa8eae219f979fcf1a5675d2ffbce93655
|
||||||
|
size 4882323744
|
||||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c8c4cdb75ec1d191d4cbb2525798c810e0c311f8b1f086030c2685536f1da803
|
||||||
|
size 4983012192
|
||||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e67bc295cea5da054c2560067fec9e0721106b528c0f9b32fd1b1857019923c5
|
||||||
|
size 4957821336
|
||||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:059935872f7bebea830cda266cb6727d4fc5d3b1531cef33e2b5c7888c6947d5
|
||||||
|
size 4303521472
|
||||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b27d28de29be8d883f75edd457ae26fecdfc101d54307f4e3b8e57ac6dc8c06d
|
||||||
|
size 1572864128
|
||||||
496
model.safetensors.index.json
Normal file
496
model.safetensors.index.json
Normal file
@@ -0,0 +1,496 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 45274656768
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.40.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.40.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.41.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.42.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.42.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.42.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.42.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.42.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.42.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.42.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.42.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.42.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.43.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.43.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.45.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.46.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.47.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.48.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.48.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.48.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.48.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.48.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.48.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.48.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.48.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.48.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.49.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.49.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.50.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.50.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.51.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.52.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.53.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.norm.weight": "model-00009-of-00010.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"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.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d6e4810e827e4ffcd735429d19d585326bb4efb31e921cb870ecefc4c1fa16e3
|
||||||
|
size 15783507
|
||||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254
|
||||||
|
size 2408875
|
||||||
2108
tokenizer_config.json
Normal file
2108
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user