初始化项目，由ModelHub XC社区提供模型
Model: OccultAI/Qliphoth-12B-v1.2 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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
401
README.md
Normal file
401
README.md
Normal file
@@ -0,0 +1,401 @@
|
||||
---
|
||||
base_model:
|
||||
- IntervitensInc/Mistral-Nemo-Base-2407-chatml
|
||||
- BrainDelay/Mistral-Nemo-BlackWidow-Agony-V1
|
||||
- DarkArtsForge/Morbid-Miasma-12B
|
||||
- DarkArtsForge/Savage-Sands-12B
|
||||
- EldritchLabs/KrakenSakura-Maelstrom-12B-v1
|
||||
- Epiculous/Violet_Twilight-v0.2
|
||||
- inflatebot/MN-12B-Mag-Mell-R1
|
||||
- LatitudeGames/Muse-12B
|
||||
- Naphula/Ancient-Awakening-12B
|
||||
- OccultAI/Qliphoth-12B-v1
|
||||
- OccultAI/Qliphoth-12B-v1.1
|
||||
- Retreatcost/Evertide-RX-12B
|
||||
- SicariusSicariiStuff/Impish_Bloodmoon_12B
|
||||
- sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B
|
||||
- Vortex5/Nether-Moon-12B
|
||||
- Vortex5/Wicked-Oblivion-12B
|
||||
- wave-on-discord/silly-v0.2
|
||||
- WokeAI/Tankie-DPE-12B-SFT-v2
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- Naphula-Archives/qliphoth_12B_minibard_bench
|
||||
- OccultAI/illuminati_imatrix_v1
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- mistral
|
||||
- nemo
|
||||
- qliphoth
|
||||
widget:
|
||||
- text: "Qliphoth-12B-v1.2"
|
||||
output:
|
||||
url: https://cdn-uploads.huggingface.co/production/uploads/69e46bb84df2a2575b60a527/DPIoVGOUmNBFcvsUsVNEw.png
|
||||
---
|
||||
|
||||
# 👾 Qliphoth 12B v1.2
|
||||
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/69e46bb84df2a2575b60a527/DPIoVGOUmNBFcvsUsVNEw.png" style="float:center; width:432px; height:592px; padding:10px;">
|
||||
|
||||
Experimental merge of previous `Qliphoth` versions with other finetunes and merges.
|
||||
|
||||
Note: Only ChatML is supported. Previous versions seemed more stable with either ChatML or Tekken.
|
||||
|
||||
The model has refusals and may require jailbreaks or ablations to fully uncensor.
|
||||
|
||||
---
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
This model was merged using the [`qliphoth`](https://huggingface.co/OccultAI/Qliphoth-12B-v1) [custom method](https://huggingface.co/24B-Suite/Mergedonia-Suite-24B-v1/discussions/3) using **mistralai/Mistral-Nemo-Instruct-2407** as a base.
|
||||
|
||||
**Qliphoth 12B** has some refusals and may require jailbreaks or ablation to fully uncensor.
|
||||
|
||||
```yaml
|
||||
architecture: MistralForCausalLM
|
||||
base_model: B:/12B/IntervitensInc--Mistral-Nemo-Base-2407-chatml
|
||||
models:
|
||||
- model: B:/12B/SicariusSicariiStuff--Impish_Bloodmoon_12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Vortex5--Wicked-Oblivion-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Vortex5--Nether-Moon-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Retreatcost--Evertide-RX-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Epiculous--Violet_Twilight-v0.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/inflatebot--MN-12B-Mag-Mell-R1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/wave-on-discord--silly-v0.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/BrainDelay--Mistral-Nemo-BlackWidow-Agony-V1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/OccultAI--Qliphoth-12B-v1
|
||||
parameters:
|
||||
pinocchio: 1.0
|
||||
- model: B:/12B/OccultAI--Qliphoth-12B-v1.1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/WokeAI--Tankie-DPE-12B-SFT-v2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/EldritchLabs--KrakenSakura-Maelstrom-12B-v1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/DarkArtsForge--Savage-Sands-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/DarkArtsForge--Morbid-Miasma-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Naphula--Ancient-Awakening-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/sleepdeprived3--Reformed-Christian-Bible-Expert-v2.1-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/LatitudeGames--Muse-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
merge_method: qliphoth
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
chat_template: "chatml"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Notes for v1 and 1.1
|
||||
|
||||
**Qliphoth 12B** has some refusals and may require jailbreaks or ablation to fully uncensor.
|
||||
|
||||
Both `Mistral Tekken` and `ChatML` chat templates are supported and may produce different results, so it's recommended to use one of those.
|
||||
|
||||
The model is very creative and produces highly varied, verbose output even at low temps. A `karcher` merge was tested using the same donors and was found to be less creative in comparison.
|
||||
|
||||
## Version 1 vs 1.1
|
||||
In my simple tests, [v1](https://huggingface.co/OccultAI/Qliphoth-12B-v1) had a distinct, visceral style and seemed to prefer `Mistral Tekken`, while [v1.1](https://huggingface.co/OccultAI/Qliphoth-12B-v1.1) was more clinical and detached, and did better with `ChatML` template.
|
||||
|
||||
Both versions performed well and were tested with [Q0 Bench](https://huggingface.co/Naphula/Q0_Bench), where v1.1 scored about 3000 points higher. They were also tested with the new [MiniBARD](https://huggingface.co/spaces/Naphula/MiniBARD) (Benchmark for Aesthetics, Roleplay & Depth). Again here, v1.1 outperformed v1. **Either version is great**, so test them both if you have time, although I may slightly prefer the style of v1.
|
||||
|
||||
|
||||
|
||||
### ⚙️ Configuration
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
<details><summary>Qliphoth 12B v1 yaml</summary>
|
||||
|
||||
```yaml
|
||||
architecture: MistralForCausalLM
|
||||
base_model: B:/12B/IntervitensInc--Mistral-Nemo-Base-2407-chatml
|
||||
models:
|
||||
- model: B:/12B/SicariusSicariiStuff--Impish_Bloodmoon_12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/NeverSleep--Lumimaid-v0.2-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/KOOWEEYUS--BlackSheep-RP-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/KOOWEEYUS--BlackSheep-RP-12B # x2 influence for the apprentice
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/TheDrummer--Rocinante-X-12B-v1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/WokeAI--Tankie-DPE-12b-SFT
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/WokeAI--Tankie-DPE-12B-SFT-v2 # pinocchio
|
||||
parameters:
|
||||
pinocchio: 1.0
|
||||
- model: B:/12B/XeyonAI--Mistral-Helcyon-Mercury-12b-v3.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/anthracite-org--magnum-v4-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/dphn--dolphin-2.9.3-mistral-nemo-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Edens-Gate--nemo-erebus-lora-2152/nemo-erebus-lora-2152
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Epiculous--Azure_Dusk-v0.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Epiculous--Crimson_Dawn-v0.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Fizzarolli--MN-12b-Rosier-v1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/HumanLLMs--Human-Like-Mistral-Nemo-Instruct-2407
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/IIEleven11--Kalypso
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Lambent--Arsenic-Shahrazad-12B-v4.1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/LatitudeGames--Wayfarer-2-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/PocketDoc--Dans-DangerousWinds-V1.1.0-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/PocketDoc--Dans-SakuraKaze-V1.0.0-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/PygmalionAI--Pygmalion-3-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/sleepdeprived3--Christian-Bible-Expert-v2.0-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/rAIfle--Questionable-MN-bf16
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/jtatman--mistral_nemo_12b_reasoning_psychology_lora/mistral_nemo_12b_reasoning_psychology_lora
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/LatitudeGames--Muse-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/allura-org--Tlacuilo-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/ChaoticNeutrals--Mag-Mell-Reasoner-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: A:/LLM/.cache/13B/taozi555--MN-12B-Mag-Mell-R1-KTO
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: A:/LLM/.cache/13B/UniLLMer--GslayerKaa
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
merge_method: qliphoth
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
chat_template: "chatml"
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details><summary>Qliphoth 12B v1.1 yaml</summary>
|
||||
|
||||
```yaml
|
||||
architecture: MistralForCausalLM
|
||||
base_model: B:/12B/IntervitensInc--Mistral-Nemo-Base-2407-chatml
|
||||
models:
|
||||
- model: B:/12B/SicariusSicariiStuff--Impish_Bloodmoon_12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/NeverSleep--Lumimaid-v0.2-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/KOOWEEYUS--BlackSheep-RP-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/nothingiisreal--MN-12B-Celeste-V1.9
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/TheDrummer--Rocinante-X-12B-v1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/WokeAI--Tankie-DPE-12b-SFT
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/WokeAI--Tankie-DPE-12B-SFT-v2 # pinocchio
|
||||
parameters:
|
||||
pinocchio: 1.0
|
||||
- model: B:/12B/XeyonAI--Mistral-Helcyon-Mercury-12b-v3.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/anthracite-org--magnum-v4-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/dphn--dolphin-2.9.3-mistral-nemo-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Edens-Gate--nemo-erebus-lora-2152/nemo-erebus-lora-2152
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Epiculous--Azure_Dusk-v0.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Epiculous--Crimson_Dawn-v0.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Fizzarolli--MN-12b-Rosier-v1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/HumanLLMs--Human-Like-Mistral-Nemo-Instruct-2407
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/IIEleven11--Kalypso
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Lambent--Arsenic-Shahrazad-12B-v4.3.2
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Lambent--Arsenic-Shahrazad-12B-v4.1
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/LatitudeGames--Wayfarer-2-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/PocketDoc--Dans-DangerousWinds-V1.1.0-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/PocketDoc--Dans-SakuraKaze-V1.0.0-12b
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/PygmalionAI--Pygmalion-3-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/sleepdeprived3--Christian-Bible-Expert-v2.0-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/rAIfle--Questionable-MN-bf16
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/jtatman--mistral_nemo_12b_reasoning_psychology_lora/mistral_nemo_12b_reasoning_psychology_lora
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/LatitudeGames--Muse-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/allura-org--Tlacuilo-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/ChaoticNeutrals--Mag-Mell-Reasoner-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: A:/LLM/.cache/13B/taozi555--MN-12B-Mag-Mell-R1-KTO
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: A:/LLM/.cache/13B/UniLLMer--GslayerKaa
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
- model: B:/12B/Retreatcost--Evertide-RX-12B
|
||||
parameters:
|
||||
pinocchio: 0.0
|
||||
merge_method: qliphoth
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
chat_template: "chatml"
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
To fix tokenizer issues while retaining enhanced intelligence of the chatml base:
|
||||
|
||||
1. I first merged the model using
|
||||
```yaml
|
||||
base_model: B:/12B/IntervitensInc--Mistral-Nemo-Base-2407-chatml
|
||||
tokenizer:
|
||||
source: base
|
||||
chat_template: "chatml"
|
||||
```
|
||||
|
||||
2. I then merged it again using
|
||||
```yaml
|
||||
base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
|
||||
tokenizer:
|
||||
source: union
|
||||
chat_template: auto
|
||||
```
|
||||
|
||||
3. I then had to modify `mergekit/tokenizer/embed.py` to allow for the passthrough merge
|
||||
```py
|
||||
token_configs[token] = TokenEmbeddingConfig(source=ZeroEmbedding(kind="zero"))
|
||||
|
||||
) -> torch.Tensor:
|
||||
if isinstance(cfg.source, ZeroEmbedding):
|
||||
first_tensor = next(iter(tensors.values()))
|
||||
embed = torch.zeros(
|
||||
first_tensor.shape[1],
|
||||
dtype=first_tensor.dtype,
|
||||
device=first_tensor.device
|
||||
)
|
||||
```
|
||||
|
||||
4. I then ran another merge to fix tokenizer issues
|
||||
```yaml
|
||||
merge_method: passthrough
|
||||
slices:
|
||||
- sources:
|
||||
- model: B:\12B\Stage1Base
|
||||
layer_range: [0, 40]
|
||||
tokenizer_source: B:\12B\Stage2Union
|
||||
chat_template: auto
|
||||
```
|
||||
|
||||
For some reason, this process produced significantly smarter output than just using `base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407`.
|
||||
|
||||
**This passthrough process using base as base_model was replicated for v1.2**
|
||||
2
chat_template.jinja
Normal file
2
chat_template.jinja
Normal file
@@ -0,0 +1,2 @@
|
||||
{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}
|
||||
{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 15,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 1024000,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131076
|
||||
}
|
||||
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:e59b8d8a3158366438d3dcfadc0fdfd035fa4880d5bbbedf1e128f60134b186d
|
||||
size 4865571256
|
||||
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 sha256:3cd15627066b347e0b5219a735a7786375d8294d4e2828dfe07bef3eaf4ec0a3
|
||||
size 4907529456
|
||||
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 sha256:1b537a3c6d8efe5edf1c180ab3ad82067942f037a9354798b8bdc0378796220a
|
||||
size 4907529464
|
||||
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:e9614ab9dde22692173f62da4d5e97887ccaa23eea148404ef95cfda07ae4173
|
||||
size 4907529456
|
||||
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:f3274f45d35e5440e1c2f54cc4bdeff4f9ee6dd76151a22ebea82e3b8a5fad3c
|
||||
size 4907529392
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24495646720,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-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-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-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-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-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-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-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-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-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-00004-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-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-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-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"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 sha256:888307b34b241bd15eb1277a16de8ea5c88aadac9007d6c509739ee30357b9c9
|
||||
size 17079038
|
||||
8050
tokenizer_config.json
Normal file
8050
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user