初始化项目，由ModelHub XC社区提供模型
Model: ajibawa-2023/Code-290k-13B Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
178
README.md
Normal file
178
README.md
Normal file
@@ -0,0 +1,178 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: cc-by-nc-nd-4.0
|
||||
tags:
|
||||
- code
|
||||
datasets:
|
||||
- ajibawa-2023/Code-290k-ShareGPT
|
||||
model-index:
|
||||
- name: Code-290k-13B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 56.06
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 81.55
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 51.99
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 37.65
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 72.69
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 17.82
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
|
||||
**Code-290k-13B**
|
||||
|
||||
Large Language Models (LLMs) are good with code generations. Sometimes they do make mistakes in code generation. How about if they can give detailed explanation along with the code.
|
||||
This is what I have tried over here. The base Llama-2 model was used for training purpose. It is trained on around **290000** set of codes. Each set having 2 conversations.
|
||||
Along with Python, Java, JavaScript, GO, C++, Rust, Ruby, Sql, MySql, R, Julia, Haskell, etc. code with detailed explanation is used for training purpose. It is built upon using my existing Datasets [Python-Code-23k-ShareGPT](https://huggingface.co/datasets/ajibawa-2023/Python-Code-23k-ShareGPT) and [Code-74k-ShareGPT](https://huggingface.co/datasets/ajibawa-2023/Code-74k-ShareGPT) .
|
||||
This conversation is in Vicuna/ShareGPT format. Each set, along with code, has detailed explanation.
|
||||
|
||||
I have released the new data [Code-290k-ShareGPT](https://huggingface.co/datasets/ajibawa-2023/Code-290k-ShareGPT) on which this Model is trained.
|
||||
|
||||
**Training:**
|
||||
|
||||
Entire dataset was trained on 4 x A100 80GB. For 3 epoch, training took 165 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.
|
||||
|
||||
|
||||
This is a full fine tuned model. Links for quantized models are given below.
|
||||
|
||||
|
||||
**GPTQ, GGUF, AWQ & Exllama**
|
||||
|
||||
GPTQ: [Link](https://huggingface.co/TheBloke/Code-290k-13B-GPTQ)
|
||||
|
||||
GGUF: [Link](https://huggingface.co/TheBloke/Code-290k-13B-GGUF)
|
||||
|
||||
AWQ: [Link](https://huggingface.co/TheBloke/Code-290k-13B-AWQ)
|
||||
|
||||
Exllama v2: [Link](https://huggingface.co/bartowski/Code-290k-13B-exl2)
|
||||
|
||||
|
||||
Extremely thankful to [TheBloke](https://huggingface.co/TheBloke) and [Bartowski](https://huggingface.co/bartowski) for making Quantized versions of the model.
|
||||
|
||||
|
||||
**Example Prompt:**
|
||||
```
|
||||
This is a conversation with your helpful AI assistant. AI assistant can generate Code in various Programming Languages along with necessary explanation.
|
||||
|
||||
Context
|
||||
You are a helpful AI assistant.
|
||||
|
||||
USER: <prompt>
|
||||
ASSISTANT:
|
||||
```
|
||||
|
||||
You can modify above Prompt as per your requirement. I have used ShareGPT/Vicuna format v1.1 .
|
||||
|
||||
I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.
|
||||
|
||||
Thank you for your love & support.
|
||||
|
||||
**Example Output**
|
||||
|
||||
Will update soon.
|
||||
# [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_ajibawa-2023__Code-290k-13B)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |52.96|
|
||||
|AI2 Reasoning Challenge (25-Shot)|56.06|
|
||||
|HellaSwag (10-Shot) |81.55|
|
||||
|MMLU (5-Shot) |51.99|
|
||||
|TruthfulQA (0-shot) |37.65|
|
||||
|Winogrande (5-shot) |72.69|
|
||||
|GSM8k (5-shot) |17.82|
|
||||
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "/media/mla100scus/Projects_1/Code-290k-13B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 40,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.28.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 0,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.28.1"
|
||||
}
|
||||
3
pytorch_model-00001-of-00004.bin
Normal file
3
pytorch_model-00001-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:075b0dae032ebc2ccadec4314fb3e286887cf55a6bfe7043e43caf0c4582a54b
|
||||
size 8575045163
|
||||
3
pytorch_model-00002-of-00004.bin
Normal file
3
pytorch_model-00002-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b73ce90c163cd4c72f3ad75aa69a7f053304b86367db2596f4fdaa315ad7f3a2
|
||||
size 8457082079
|
||||
3
pytorch_model-00003-of-00004.bin
Normal file
3
pytorch_model-00003-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:85073abf0e044859bb895ce46fc3238d72fa9bedf847b44241d0c3a9b58c4fa3
|
||||
size 8530481246
|
||||
3
pytorch_model-00004-of-00004.bin
Normal file
3
pytorch_model-00004-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2b6fb5bac0b52a486679edbfc03ba5074fd2d4113e6ea9e0b80779c59cf7d956
|
||||
size 469271113
|
||||
410
pytorch_model.bin.index.json
Normal file
410
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,410 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26031738880
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.norm.weight": "pytorch_model-00004-of-00004.bin"
|
||||
}
|
||||
}
|
||||
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": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93385
tokenizer.json
Normal file
93385
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user