初始化项目，由ModelHub XC社区提供模型
Model: migtissera/Tess-10.7B-v1.5 Source: Original Platform
This commit is contained in:
ModelHub XC
55
.gitattributes
vendored
Normal file
55
.gitattributes
vendored
Normal file
@@ -0,0 +1,55 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
|
||||
*.bz2 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
|
||||
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
pytorch_model-00003-of-00005.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00002-of-00005.bin filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00005-of-00005.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00004-of-00005.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00001-of-00005.bin filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
||||
139
README.md
Normal file
139
README.md
Normal file
@@ -0,0 +1,139 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
model-index:
|
||||
- name: Tess-10.7B-v1.5
|
||||
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: 65.02
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-10.7B-v1.5
|
||||
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: 84.07
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-10.7B-v1.5
|
||||
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: 65.09
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-10.7B-v1.5
|
||||
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: 47.43
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-10.7B-v1.5
|
||||
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: 83.35
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-10.7B-v1.5
|
||||
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: 54.36
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-10.7B-v1.5
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# Please use the updated version Tess-10.7B-v1.5b
|
||||
Tess-10.7B-v1.5b has hyperparameter optimizations. Access at: https://huggingface.co/migtissera/Tess-10.7B-v1.5b
|
||||
|
||||
<br>
|
||||
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-10.7B-v1.5 was trained on the SOLAR-10.7B base.
|
||||
|
||||
|
||||
# Prompt Format:
|
||||
|
||||
```
|
||||
SYSTEM: <ANY SYSTEM CONTEXT>
|
||||
USER:
|
||||
ASSISTANT:
|
||||
```
|
||||
# [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_migtissera__Tess-10.7B-v1.5)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |66.55|
|
||||
|AI2 Reasoning Challenge (25-Shot)|65.02|
|
||||
|HellaSwag (10-Shot) |84.07|
|
||||
|MMLU (5-Shot) |65.09|
|
||||
|TruthfulQA (0-shot) |47.43|
|
||||
|Winogrande (5-shot) |83.35|
|
||||
|GSM8k (5-shot) |54.36|
|
||||
|
||||
BIN
Tess-v1-5.png
Normal file
BIN
Tess-v1-5.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 457 KiB |
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "/home/migel/SOLAR-10.7B-v1.0",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.36.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.36.2",
|
||||
"use_cache": false
|
||||
}
|
||||
3
pytorch_model-00001-of-00005.bin
Normal file
3
pytorch_model-00001-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:237ac0e9d59e79011e138142fb8849542be42260f9ec25edb43665ee6ea38dfa
|
||||
size 4943185145
|
||||
3
pytorch_model-00002-of-00005.bin
Normal file
3
pytorch_model-00002-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4876f851323c75db10c5aae6420ba3dc9bddbcae8153ca628a22ebb0f7168f3
|
||||
size 4999844257
|
||||
3
pytorch_model-00003-of-00005.bin
Normal file
3
pytorch_model-00003-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42613dbfd7fe52fc93a283254800497a1274b126f39454c3d4833df4b8232332
|
||||
size 4915939683
|
||||
3
pytorch_model-00004-of-00005.bin
Normal file
3
pytorch_model-00004-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6d8f579e685db7f522b1d666a794784674dd45fa3752df32c33721b68c534094
|
||||
size 4915939683
|
||||
3
pytorch_model-00005-of-00005.bin
Normal file
3
pytorch_model-00005-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd7b31b94820347d05671888d8564f4e2f67f22094fa87519fa066f2d3eedca8
|
||||
size 1688292111
|
||||
442
pytorch_model.bin.index.json
Normal file
442
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,442 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 21463048192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.norm.weight": "pytorch_model-00005-of-00005.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": "</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:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc
|
||||
size 1795303
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
42
tokenizer_config.json
Normal file
42
tokenizer_config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user