初始化项目，由ModelHub XC社区提供模型
Model: Locutusque/lr-experiment1-7B 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
|
||||
43
README.md
Normal file
43
README.md
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- Locutusque/hercules-v2.0
|
||||
- CollectiveCognition/chats-data-2023-09-22
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# lr-experiment1-7B
|
||||
|
||||
The lr-experiment model series is a research project I'm conducting that I will be using to determine the best learning rate to use while fine-tuning Mistral. This model uses a learning rate of 2e-5 with a cosine scheduler and no warmup steps.
|
||||
|
||||
I used Locutusque/Hercules-2.0-Mistral-7B as a base model, and further fine-tuned it on CollectiveCognition/chats-data-2023-09-22 using QLoRA for 3 epochs. I will be keeping track of evaluation results, and will comparing it to upcoming models.
|
||||
|
||||
# Evals
|
||||
|
||||
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
||||
|---------------------------------|-------|------|------|--------|-----:|---|-----:|
|
||||
|agieval_nous |N/A |none |None |acc |0.3645|± |0.0093|
|
||||
| | |none |None |acc_norm|0.3468|± |0.0092|
|
||||
| - agieval_aqua_rat | 1|none |None |acc |0.2283|± |0.0264|
|
||||
| | |none |None |acc_norm|0.2283|± |0.0264|
|
||||
| - agieval_logiqa_en | 1|none |None |acc |0.2965|± |0.0179|
|
||||
| | |none |None |acc_norm|0.3303|± |0.0184|
|
||||
| - agieval_lsat_ar | 1|none |None |acc |0.2217|± |0.0275|
|
||||
| | |none |None |acc_norm|0.1783|± |0.0253|
|
||||
| - agieval_lsat_lr | 1|none |None |acc |0.4039|± |0.0217|
|
||||
| | |none |None |acc_norm|0.3686|± |0.0214|
|
||||
| - agieval_lsat_rc | 1|none |None |acc |0.4870|± |0.0305|
|
||||
| | |none |None |acc_norm|0.4424|± |0.0303|
|
||||
| - agieval_sat_en | 1|none |None |acc |0.6408|± |0.0335|
|
||||
| | |none |None |acc_norm|0.5971|± |0.0343|
|
||||
| - agieval_sat_en_without_passage| 1|none |None |acc |0.3932|± |0.0341|
|
||||
| | |none |None |acc_norm|0.3835|± |0.0340|
|
||||
| - agieval_sat_math | 1|none |None |acc |0.3455|± |0.0321|
|
||||
| | |none |None |acc_norm|0.2727|± |0.0301|
|
||||
|
||||
| Groups |Version|Filter|n-shot| Metric |Value | |Stderr|
|
||||
|------------|-------|------|------|--------|-----:|---|-----:|
|
||||
|agieval_nous|N/A |none |None |acc |0.3645|± |0.0093|
|
||||
| | |none |None |acc_norm|0.3468|± |0.0092|
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "Locutusque/Hercules-2.0-Mistral-7B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"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": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.38.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.38.2"
|
||||
}
|
||||
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:41fcbe095938c4d9acd852597677100d8e7a0d64cf43b0a3178ed986bf8965fc
|
||||
size 1889587008
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:06bbef310a3e9f7512810cca33ab733aeb92c6bc43fd7cd90335b998dc8e5856
|
||||
size 1946243896
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8fe8865e516cfbad626b6ce675d4840c836e17c725f3af384a5a5a1072b774ab
|
||||
size 1979781392
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ae087faacdf0f2a4e248f17ae78b492c5c902024f1dd9149e0ceed0b08897a9d
|
||||
size 1946243936
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:255cdb8377f743e99bba8ecb6701dfb12ffb9cf03c99674c27cc9db12da79ce5
|
||||
size 1979781416
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b781f2edee4bff90f94976152a7f8e2eb153db546047a23b6c91bacd35c212c
|
||||
size 1946243936
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9599adea8e1303306da26883b314dfb3968b9601ccf5d48de21d513b3331dfd3
|
||||
size 1979781416
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd5a8839c76bd571df2e4bf688a8eea8ee6c959a1611df3e999b7ca2c19a1821
|
||||
size 815834664
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00008-of-00008.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00008.safetensors"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</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
|
||||
}
|
||||
}
|
||||
91136
tokenizer.json
Normal file
91136
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.
50
tokenizer_config.json
Normal file
50
tokenizer_config.json
Normal file
@@ -0,0 +1,50 @@
|
||||
{
|
||||
"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>",
|
||||
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"max_length": 512,
|
||||
"model_max_length": 32768,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "</s>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"stride": 0,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user