初始化项目，由ModelHub XC社区提供模型
Model: anjohn0077/NEXS-deepseek-7b-multislerp 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
|
||||
50
README.md
Normal file
50
README.md
Normal file
@@ -0,0 +1,50 @@
|
||||
---
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- multislerp
|
||||
- task-vector
|
||||
base_model:
|
||||
- deepseek-ai/deepseek-llm-7b-base
|
||||
- deepseek-ai/deepseek-math-7b-instruct
|
||||
- deepseek-ai/deepseek-coder-7b-instruct-v1.5
|
||||
---
|
||||
|
||||
# NEXS Deepseek-7B Multi-SLERP Merge
|
||||
|
||||
A multi-SLERP merge of LlamaForCausalLM domain experts covering **math and code**, produced with
|
||||
[mergekit](https://github.com/arcee-ai/mergekit). Part of the
|
||||
[NEXS multi-SLERP merge collection](https://huggingface.co/anjohn0077/NEXS-multislerp-merges).
|
||||
|
||||
## Method
|
||||
|
||||
Multi-SLERP (`multislerp`) performs barycentric spherical interpolation on a hypersphere for more than two models: it projects the models into the tangent space at their weighted Euclidean mean, interpolates, and projects back. Here it is run in **task-vector space** — each source's delta from the shared base model is computed, the deltas are spherically averaged with equal weight (`normalize_weights: true`, `eps: 1e-8`), and the result is added back to the base. Merging was done with [mergekit](https://github.com/arcee-ai/mergekit).
|
||||
|
||||
All variants share an identical vocabulary (102400); no tokenizer reconciliation was needed.
|
||||
|
||||
## Sources
|
||||
|
||||
Base model (task-vector reference): [`deepseek-ai/deepseek-llm-7b-base`](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
|
||||
|
||||
Merged variants (equal weight `1.0` each):
|
||||
- [`deepseek-ai/deepseek-math-7b-instruct`](https://huggingface.co/deepseek-ai/deepseek-math-7b-instruct)
|
||||
- [`deepseek-ai/deepseek-coder-7b-instruct-v1.5`](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5)
|
||||
|
||||
## mergekit config
|
||||
|
||||
```yaml
|
||||
merge_method: multislerp
|
||||
base_model: deepseek-ai/deepseek-llm-7b-base
|
||||
tokenizer_source: base
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
parameters:
|
||||
normalize_weights: true
|
||||
eps: 1.0e-8
|
||||
models:
|
||||
- model: deepseek-ai/deepseek-math-7b-instruct
|
||||
parameters: {weight: 1.0}
|
||||
- model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
|
||||
parameters: {weight: 1.0}
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 30,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 100015
|
||||
}
|
||||
13
mergekit_config.yml
Normal file
13
mergekit_config.yml
Normal file
@@ -0,0 +1,13 @@
|
||||
merge_method: multislerp
|
||||
base_model: deepseek-ai/deepseek-llm-7b-base
|
||||
tokenizer_source: base
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
parameters:
|
||||
normalize_weights: true
|
||||
eps: 1.0e-8
|
||||
models:
|
||||
- model: deepseek-ai/deepseek-math-7b-instruct
|
||||
parameters: {weight: 1.0}
|
||||
- model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
|
||||
parameters: {weight: 1.0}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d10adecf5e70bba0de81fcd5bbfb2e59dda0aa0ec274441ded876cb39a9fa68
|
||||
size 4966974096
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7edfb0c036017512ccefb88c0a9ce0b5c55cd2515d8607a609afdc2004e66234
|
||||
size 4947390888
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8677e8039d36a281069719addaccaa426847f46f5251660163c41b5f59f1fa5a
|
||||
size 3867322312
|
||||
281
model.safetensors.index.json
Normal file
281
model.safetensors.index.json
Normal file
@@ -0,0 +1,281 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13781655552,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
499303
tokenizer.json
Normal file
499303
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
138
tokenizer_config.json
Normal file
138
tokenizer_config.json
Normal file
@@ -0,0 +1,138 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"100000": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100001": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100002": {
|
||||
"content": "ø",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100003": {
|
||||
"content": "ö",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100004": {
|
||||
"content": "ú",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100005": {
|
||||
"content": "ÿ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100006": {
|
||||
"content": "õ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100007": {
|
||||
"content": "÷",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100008": {
|
||||
"content": "û",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100009": {
|
||||
"content": "ý",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100010": {
|
||||
"content": "À",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100011": {
|
||||
"content": "ù",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100012": {
|
||||
"content": "Á",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100013": {
|
||||
"content": "þ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100014": {
|
||||
"content": "ü",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<｜end▁of▁sentence｜>",
|
||||
"extra_special_tokens": {},
|
||||
"legacy": true,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<｜end▁of▁sentence｜>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizerFast",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user