初始化项目，由ModelHub XC社区提供模型
Model: Anannta/R1-Coder-DARE-7B Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
R1-Coder-DARE-7B-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
R1-Coder-DARE-7B-F16.gguf
Normal file
3
R1-Coder-DARE-7B-F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:71bef35538bdf2cef9cc3454c89b1ff964e52cce32a83209a38da7f25e509aed
|
||||
size 15232124096
|
||||
43
README.md
Normal file
43
README.md
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
base_model:
|
||||
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
||||
- Qwen/Qwen2.5-Coder-7B-Instruct
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# R1-Coder-DARE-7B
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
## Merge Details
|
||||
### Merge Method
|
||||
|
||||
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
models:
|
||||
- model: Qwen/Qwen2.5-Coder-7B-Instruct
|
||||
parameters:
|
||||
density: 0.50
|
||||
weight: 0.50
|
||||
merge_method: ties
|
||||
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
||||
parameters:
|
||||
normalize: true
|
||||
int8_mask: true
|
||||
dtype: bfloat16
|
||||
tokenizer_source: base
|
||||
|
||||
```
|
||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal file
@@ -0,0 +1 @@
|
||||
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
|
||||
62
config.json
Normal file
62
config.json
Normal file
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 10000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.0.0",
|
||||
"use_cache": true,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151665
|
||||
}
|
||||
12
mergekit_config.yml
Normal file
12
mergekit_config.yml
Normal file
@@ -0,0 +1,12 @@
|
||||
models:
|
||||
- model: Qwen/Qwen2.5-Coder-7B-Instruct
|
||||
parameters:
|
||||
density: 0.50
|
||||
weight: 0.50
|
||||
merge_method: ties
|
||||
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
||||
parameters:
|
||||
normalize: true
|
||||
int8_mask: true
|
||||
dtype: bfloat16
|
||||
tokenizer_source: base
|
||||
3
model-00001-of-00017.safetensors
Normal file
3
model-00001-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fccc6bd9914bb891539f3b3211897fbcf457833cc13f1006c95fee5d7380e3f6
|
||||
size 972700864
|
||||
3
model-00002-of-00017.safetensors
Normal file
3
model-00002-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ec53cdf43284a35ee9613cb4f5c156d51870fd75037742b345e5c66ee9ba81c6
|
||||
size 557935280
|
||||
3
model-00003-of-00017.safetensors
Normal file
3
model-00003-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a15be0f7902a4099a8f980c3420295940beac89cfe147b113f9591c836c4f9c0
|
||||
size 1087134848
|
||||
3
model-00004-of-00017.safetensors
Normal file
3
model-00004-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:724e2f210a78c56a308440bf3bc79614f8bac29499f9d2c38734fd626c11c1b5
|
||||
size 976386704
|
||||
3
model-00005-of-00017.safetensors
Normal file
3
model-00005-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2b72c8b95b0747ffe7c63a5f3fea52805d4ba1eac069595a642ff762a3b74442
|
||||
size 278967656
|
||||
3
model-00006-of-00017.safetensors
Normal file
3
model-00006-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13d168bc35ef1e1a02eceb11c48bbba7aa65edf6474edfa95862126926303cde
|
||||
size 1087134864
|
||||
3
model-00007-of-00017.safetensors
Normal file
3
model-00007-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5ed8fdd972dfdc5915e6400cac316d86ccaa9e61a28b87b6f8c58532b42d515f
|
||||
size 884568392
|
||||
3
model-00008-of-00017.safetensors
Normal file
3
model-00008-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bc021df350e86b4ab064b24509745b726077e3b73649d4ffb0d174ff29276cbb
|
||||
size 935927000
|
||||
3
model-00009-of-00017.safetensors
Normal file
3
model-00009-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed6e5a885bb4628af04c64589400c9d6ea460a2f50ab0580bca872b4f3fd7162
|
||||
size 932233880
|
||||
3
model-00010-of-00017.safetensors
Normal file
3
model-00010-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:99b0c164bac21da409640eb3d0c2fc5b80be3bcac876eba45aef1a10f304b81e
|
||||
size 979899424
|
||||
3
model-00011-of-00017.safetensors
Normal file
3
model-00011-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9ec1e69745d56bd13b620b7412fb494fe0dfad24388be9169f991d35e85334d0
|
||||
size 979899424
|
||||
3
model-00012-of-00017.safetensors
Normal file
3
model-00012-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:71a0489cd154e38f3016578278bf1a4bbb5d007aa64f94bfa5f04faef472cdcf
|
||||
size 979899416
|
||||
3
model-00013-of-00017.safetensors
Normal file
3
model-00013-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e01cd14a3a38838cb71549b7cd37e92850d038f24ba901d9c1d57b5ec50aff61
|
||||
size 979899424
|
||||
3
model-00014-of-00017.safetensors
Normal file
3
model-00014-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c5e47e18d4374fe55042c1f9ab964a47e39471e399ff74ec3be0102843c8cfc5
|
||||
size 979899424
|
||||
3
model-00015-of-00017.safetensors
Normal file
3
model-00015-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:404d8e1832b64d839216a0a41cb101d2e92922befeb869832b9cdeedde41115c
|
||||
size 979899408
|
||||
3
model-00016-of-00017.safetensors
Normal file
3
model-00016-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b6660d4bead3468d90a845c5481fc25cef1f0a4b7d9aa43ecbbe4689cde108b
|
||||
size 979899408
|
||||
3
model-00017-of-00017.safetensors
Normal file
3
model-00017-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78983d9083b1e743ec424df4932391ecb29675b851aaa90ef58aae9345d5d245
|
||||
size 653266280
|
||||
347
model.safetensors.index.json
Normal file
347
model.safetensors.index.json
Normal file
@@ -0,0 +1,347 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15225512960,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"lm_head.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.embed_tokens.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
|
||||
"model.norm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00017-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00017-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00017-of-00017.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
|
||||
size 11421911
|
||||
13
tokenizer_config.json
Normal file
13
tokenizer_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<｜end▁of▁sentence｜>",
|
||||
"is_local": false,
|
||||
"legacy": true,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "<｜end▁of▁sentence｜>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "Qwen2TokenizerFast",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user