初始化项目，由ModelHub XC社区提供模型
Model: macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.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
|
||||||
|
orca-bagel.png filter=lfs diff=lfs merge=lfs -text
|
||||||
231
README.md
Normal file
231
README.md
Normal file
@@ -0,0 +1,231 @@
|
|||||||
|
---
|
||||||
|
license: cc
|
||||||
|
library_name: transformers
|
||||||
|
model-index:
|
||||||
|
- name: SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
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: 72.1
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
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: 88.44
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
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: 65.45
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
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: 76.75
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
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: 82.72
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
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: 59.21
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
# SOLAR-10.7b-Instruct-truthy-dpo
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
This model is a finetune of [macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo](https://huggingface.co/macadeliccc/SOLAR-10.7b-Instruct-dpo)
|
||||||
|
|
||||||
|
## Process
|
||||||
|
|
||||||
|
1. I finetuned upstageai/Solar-10.7b-Instruct-v0.1 with 1 epoch of Intel/orca_dpo_pairs (12.4k samples)
|
||||||
|
2. I futher finetuned that model with 3 epochs of jondurbin/truthy-dpo-v0.1 (1.04k samples)
|
||||||
|
3. This process is experimental and the base model linked above is more tested at this time.
|
||||||
|
|
||||||
|
## GGUF
|
||||||
|
|
||||||
|
Available [here](https://huggingface.co/macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo-GGUF)
|
||||||
|
|
||||||
|
## Evaluations
|
||||||
|
|
||||||
|
----Benchmark Complete----
|
||||||
|
+ 2024-01-26 20:57:38
|
||||||
|
+ Time taken: 25.4 mins
|
||||||
|
+ Prompt Format: ChatML
|
||||||
|
+ Model: macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo-GGUF
|
||||||
|
+ Score (v2): 74.11
|
||||||
|
+ Parseable: 171.0
|
||||||
|
---------------
|
||||||
|
Batch completed
|
||||||
|
Time taken: 25.5 mins
|
||||||
|
---------------
|
||||||
|
|
||||||
|
|
||||||
|
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
||||||
|
|-----------------------------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
||||||
|
|[SOLAR-10.7b-Instruct-truthy-dpo](https://huggingface.co/macadeliccc/SOLAR-10.7b-Instruct-truthy-dpo)| 48.69| 73.82| 76.81| 45.71| 61.26|
|
||||||
|
|
||||||
|
### AGIEval
|
||||||
|
| Task |Version| Metric |Value| |Stderr|
|
||||||
|
|------------------------------|------:|--------|----:|---|-----:|
|
||||||
|
|agieval_aqua_rat | 0|acc |27.95|± | 2.82|
|
||||||
|
| | |acc_norm|27.95|± | 2.82|
|
||||||
|
|agieval_logiqa_en | 0|acc |42.40|± | 1.94|
|
||||||
|
| | |acc_norm|42.24|± | 1.94|
|
||||||
|
|agieval_lsat_ar | 0|acc |25.65|± | 2.89|
|
||||||
|
| | |acc_norm|23.91|± | 2.82|
|
||||||
|
|agieval_lsat_lr | 0|acc |54.12|± | 2.21|
|
||||||
|
| | |acc_norm|54.51|± | 2.21|
|
||||||
|
|agieval_lsat_rc | 0|acc |69.89|± | 2.80|
|
||||||
|
| | |acc_norm|69.89|± | 2.80|
|
||||||
|
|agieval_sat_en | 0|acc |80.10|± | 2.79|
|
||||||
|
| | |acc_norm|80.10|± | 2.79|
|
||||||
|
|agieval_sat_en_without_passage| 0|acc |50.00|± | 3.49|
|
||||||
|
| | |acc_norm|49.51|± | 3.49|
|
||||||
|
|agieval_sat_math | 0|acc |42.27|± | 3.34|
|
||||||
|
| | |acc_norm|41.36|± | 3.33|
|
||||||
|
|
||||||
|
Average: 48.69%
|
||||||
|
|
||||||
|
### GPT4All
|
||||||
|
| Task |Version| Metric |Value| |Stderr|
|
||||||
|
|-------------|------:|--------|----:|---|-----:|
|
||||||
|
|arc_challenge| 0|acc |59.90|± | 1.43|
|
||||||
|
| | |acc_norm|63.91|± | 1.40|
|
||||||
|
|arc_easy | 0|acc |80.85|± | 0.81|
|
||||||
|
| | |acc_norm|78.16|± | 0.85|
|
||||||
|
|boolq | 1|acc |88.20|± | 0.56|
|
||||||
|
|hellaswag | 0|acc |68.34|± | 0.46|
|
||||||
|
| | |acc_norm|86.39|± | 0.34|
|
||||||
|
|openbookqa | 0|acc |37.60|± | 2.17|
|
||||||
|
| | |acc_norm|46.80|± | 2.23|
|
||||||
|
|piqa | 0|acc |78.84|± | 0.95|
|
||||||
|
| | |acc_norm|78.78|± | 0.95|
|
||||||
|
|winogrande | 0|acc |74.51|± | 1.22|
|
||||||
|
|
||||||
|
Average: 73.82%
|
||||||
|
|
||||||
|
### TruthfulQA
|
||||||
|
| Task |Version|Metric|Value| |Stderr|
|
||||||
|
|-------------|------:|------|----:|---|-----:|
|
||||||
|
|truthfulqa_mc| 1|mc1 |61.81|± | 1.70|
|
||||||
|
| | |mc2 |76.81|± | 1.42|
|
||||||
|
|
||||||
|
Average: 76.81%
|
||||||
|
|
||||||
|
### Bigbench
|
||||||
|
| Task |Version| Metric |Value| |Stderr|
|
||||||
|
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|
||||||
|
|bigbench_causal_judgement | 0|multiple_choice_grade|50.53|± | 3.64|
|
||||||
|
|bigbench_date_understanding | 0|multiple_choice_grade|63.14|± | 2.51|
|
||||||
|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|47.67|± | 3.12|
|
||||||
|
|bigbench_geometric_shapes | 0|multiple_choice_grade|26.18|± | 2.32|
|
||||||
|
| | |exact_str_match | 0.00|± | 0.00|
|
||||||
|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|28.60|± | 2.02|
|
||||||
|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|21.29|± | 1.55|
|
||||||
|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|47.33|± | 2.89|
|
||||||
|
|bigbench_movie_recommendation | 0|multiple_choice_grade|39.80|± | 2.19|
|
||||||
|
|bigbench_navigate | 0|multiple_choice_grade|63.80|± | 1.52|
|
||||||
|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|59.05|± | 1.10|
|
||||||
|
|bigbench_ruin_names | 0|multiple_choice_grade|40.18|± | 2.32|
|
||||||
|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|46.69|± | 1.58|
|
||||||
|
|bigbench_snarks | 0|multiple_choice_grade|65.19|± | 3.55|
|
||||||
|
|bigbench_sports_understanding | 0|multiple_choice_grade|72.41|± | 1.42|
|
||||||
|
|bigbench_temporal_sequences | 0|multiple_choice_grade|60.30|± | 1.55|
|
||||||
|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|25.76|± | 1.24|
|
||||||
|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|17.43|± | 0.91|
|
||||||
|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|47.33|± | 2.89|
|
||||||
|
|
||||||
|
Average: 45.71%
|
||||||
|
|
||||||
|
Average score: 61.26%
|
||||||
|
|
||||||
|
Elapsed time: 02:16:03
|
||||||
|
# [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_macadeliccc__SOLAR-10.7b-Instruct-truthy-dpo)
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|---------------------------------|----:|
|
||||||
|
|Avg. |74.11|
|
||||||
|
|AI2 Reasoning Challenge (25-Shot)|72.10|
|
||||||
|
|HellaSwag (10-Shot) |88.44|
|
||||||
|
|MMLU (5-Shot) |65.45|
|
||||||
|
|TruthfulQA (0-shot) |76.75|
|
||||||
|
|Winogrande (5-shot) |82.72|
|
||||||
|
|GSM8k (5-shot) |59.21|
|
||||||
|
|
||||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "macadeliccc/SOLAR-10.7b-Instruct-dpo",
|
||||||
|
"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,
|
||||||
|
"pad_token_id": 2,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.37.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 2,
|
||||||
|
"transformers_version": "4.37.1",
|
||||||
|
"use_cache": false
|
||||||
|
}
|
||||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f19b3b5ca10e2ae0ca5d92e7aae7183ae278b4f9183721cca747e7debe56d991
|
||||||
|
size 4943162240
|
||||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:734dd4cb1e6355b58431a16f5ea83bd88a7761fef6dd1fd2917a678194b0916e
|
||||||
|
size 4999819232
|
||||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:28698f4fb26120ee8a7e3c4971ab6904f22e9e6142447063c64658eab89ed9bb
|
||||||
|
size 4915916080
|
||||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a970c2eac56c2d18f9479ebf6b47a379775e85696bd6a77d8c71fa79ab01cfe0
|
||||||
|
size 4915916080
|
||||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:743b543fb140df8541334a61d56b08b0aac5a58231ef494fa1360fe26f72fb3a
|
||||||
|
size 1688284744
|
||||||
442
model.safetensors.index.json
Normal file
442
model.safetensors.index.json
Normal file
@@ -0,0 +1,442 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 21463048192
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.44.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
3
orca-bagel.png
Normal file
3
orca-bagel.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d0267454212a7cce2d128b442bb48afac603aa6d4debb9e03de0d5017de5fb6b
|
||||||
|
size 1810733
|
||||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"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": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
91122
tokenizer.json
Normal file
91122
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.
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
|||||||
|
{
|
||||||
|
"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 %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
|
||||||
|
"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