初始化项目，由ModelHub XC社区提供模型
Model: jan-hq/stealth-v2 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
172
README.md
Normal file
172
README.md
Normal file
@@ -0,0 +1,172 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
model-index:
|
||||
- name: stealth-v2
|
||||
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: 73.89
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v2
|
||||
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: 89.26
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v2
|
||||
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: 64.94
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v2
|
||||
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: 72.47
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v2
|
||||
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: 88.0
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v2
|
||||
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: 69.67
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v2
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
<!-- header start -->
|
||||
<!-- 200823 -->
|
||||
|
||||
<div style="width: auto; margin-left: auto; margin-right: auto"
|
||||
>
|
||||
<img src="https://github.com/janhq/jan/assets/89722390/35daac7d-b895-487c-a6ac-6663daaad78e" alt="Jan banner"
|
||||
style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
||||
</div>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://jan.ai/">Jan</a
|
||||
>
|
||||
- <a href="https://discord.gg/AsJ8krTT3N">Discord</a>
|
||||
</p>
|
||||
<!-- header end -->
|
||||
|
||||
|
||||
# Prompt template
|
||||
|
||||
ChatML
|
||||
```
|
||||
<|im_start|>system
|
||||
{system_message}<|im_end|>
|
||||
<|im_start|>user
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
|
||||
```
|
||||
|
||||
# Training detail
|
||||
You can read [here](https://huggingface.co/jan-hq/stealth-finance-v1-adapter).
|
||||
|
||||
# Run this model
|
||||
You can run this model using [Jan Desktop](https://jan.ai/) on Mac, Windows, or Linux.
|
||||
|
||||
Jan is an open source, ChatGPT alternative that is:
|
||||
|
||||
- 💻 **100% offline on your machine**: Your conversations remain confidential, and visible only to you.
|
||||
- 🗂️ **
|
||||
An Open File Format**: Conversations and model settings stay on your computer and can be exported or deleted at any time.
|
||||
- 🌐 **OpenAI Compatible**: Local server on port `1337` with OpenAI compatible endpoints
|
||||
|
||||
- 🌍 **Open Source & Free**: We build in public; check out our [Github](https://github.com/janhq)
|
||||
|
||||
|
||||
|
||||
|
||||
# About Jan
|
||||
Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.
|
||||
|
||||
Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.
|
||||
# [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_jan-hq__stealth-v2)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |76.37|
|
||||
|AI2 Reasoning Challenge (25-Shot)|73.89|
|
||||
|HellaSwag (10-Shot) |89.26|
|
||||
|MMLU (5-Shot) |64.94|
|
||||
|TruthfulQA (0-shot) |72.47|
|
||||
|Winogrande (5-shot) |88.00|
|
||||
|GSM8k (5-shot) |69.67|
|
||||
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "TomGrc/FusionNet_7Bx2_MoE_v0.1",
|
||||
"architectures": [
|
||||
"MixtralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mixtral",
|
||||
"num_attention_heads": 32,
|
||||
"num_experts_per_tok": 2,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"num_local_experts": 2,
|
||||
"output_router_logits": false,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"router_aux_loss_coef": 0.001,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.37.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.37.2",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46fd80516d46bf7ad5ccf8a9a99a302b681ae6223957fcf6a3ffafac4fc2f7ec
|
||||
size 4993525264
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c23c6748fddee0bc349a56fe46987e9135e9328d92501844c3943138ad39aa64
|
||||
size 4932724880
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d51e662a5c13406783247849927946b877697dded23100df82684e2b74bb7511
|
||||
size 4966262528
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c70973834574ed4dc7943ed6a751e3327d23164c2d1514d9b2fa9334ee1ca815
|
||||
size 4966262528
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a54a39825d738bc9ee6ba8f160356de7ab148500833085c681ec286bc9cc43e
|
||||
size 4932741544
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:db6471c97e88e6ace5db6776f57240d170ab91438fae3b8e1abee03f9949e4f0
|
||||
size 966812872
|
||||
426
model.safetensors.index.json
Normal file
426
model.safetensors.index.json
Normal file
@@ -0,0 +1,426 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 25758277632
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
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
|
||||
}
|
||||
}
|
||||
91129
tokenizer.json
Normal file
91129
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.
46
tokenizer_config.json
Normal file
46
tokenizer_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"max_length": null,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<s>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user