初始化项目，由ModelHub XC社区提供模型
Model: jack009064/Affine-mmh2-5EptJ5DkkearraPC65QFsPbkHkB1BZnNfoeJ5iLKeNXJGUR2 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
68
README.md
Normal file
68
README.md
Normal file
@@ -0,0 +1,68 @@
|
||||
---
|
||||
library_name: transformers
|
||||
model_name: model_output_dpo
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- dpo
|
||||
- trl
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for model_output_dpo
|
||||
|
||||
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="None", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.29.1
|
||||
- Transformers: 5.3.0
|
||||
- Pytorch: 2.6.0+cu124
|
||||
- Datasets: 4.8.4
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
Cite DPO as:
|
||||
|
||||
```bibtex
|
||||
@inproceedings{rafailov2023direct,
|
||||
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
|
||||
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
|
||||
year = 2023,
|
||||
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
|
||||
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
|
||||
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
|
||||
}
|
||||
```
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@software{vonwerra2020trl,
|
||||
title = {{TRL: Transformers Reinforcement Learning}},
|
||||
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||
license = {Apache-2.0},
|
||||
url = {https://github.com/huggingface/trl},
|
||||
year = {2020}
|
||||
}
|
||||
```
|
||||
88
chat_template.jinja
Normal file
88
chat_template.jinja
Normal file
@@ -0,0 +1,88 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- generation -%}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endgeneration -%}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
99
config.json
Normal file
99
config.json
Normal file
@@ -0,0 +1,99 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 25600,
|
||||
"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",
|
||||
"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",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 64,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 64,
|
||||
"num_hidden_layers": 64,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.3.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.3.0"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9913a6bad01be5a3cdc978c701c6155bb3da25f10124e27303a290ebbdee8278
|
||||
size 49921162112
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d646c217b47de1632c2b7ca1d8cb4b07ba0e386d5bf229e11b0a539266be5969
|
||||
size 15603167272
|
||||
715
model.safetensors.index.json
Normal file
715
model.safetensors.index.json
Normal file
@@ -0,0 +1,715 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 32762123264,
|
||||
"total_size": 65524246528
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.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:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
15
tokenizer_config.json
Normal file
15
tokenizer_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user