初始化项目，由ModelHub XC社区提供模型
Model: teolm30/Fox-1.5 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
|
||||||
|
*.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
202
LICENSE
Normal file
202
LICENSE
Normal file
@@ -0,0 +1,202 @@
|
|||||||
|
|
||||||
|
Apache License
|
||||||
|
Version 2.0, January 2004
|
||||||
|
http://www.apache.org/licenses/
|
||||||
|
|
||||||
|
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||||
|
|
||||||
|
1. Definitions.
|
||||||
|
|
||||||
|
"License" shall mean the terms and conditions for use, reproduction,
|
||||||
|
and distribution as defined by Sections 1 through 9 of this document.
|
||||||
|
|
||||||
|
"Licensor" shall mean the copyright owner or entity authorized by
|
||||||
|
the copyright owner that is granting the License.
|
||||||
|
|
||||||
|
"Legal Entity" shall mean the union of the acting entity and all
|
||||||
|
other entities that control, are controlled by, or are under common
|
||||||
|
control with that entity. For the purposes of this definition,
|
||||||
|
"control" means (i) the power, direct or indirect, to cause the
|
||||||
|
direction or management of such entity, whether by contract or
|
||||||
|
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||||
|
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||||
|
|
||||||
|
"You" (or "Your") shall mean an individual or Legal Entity
|
||||||
|
exercising permissions granted by this License.
|
||||||
|
|
||||||
|
"Source" form shall mean the preferred form for making modifications,
|
||||||
|
including but not limited to software source code, documentation
|
||||||
|
source, and configuration files.
|
||||||
|
|
||||||
|
"Object" form shall mean any form resulting from mechanical
|
||||||
|
transformation or translation of a Source form, including but
|
||||||
|
not limited to compiled object code, generated documentation,
|
||||||
|
and conversions to other media types.
|
||||||
|
|
||||||
|
"Work" shall mean the work of authorship, whether in Source or
|
||||||
|
Object form, made available under the License, as indicated by a
|
||||||
|
copyright notice that is included in or attached to the work
|
||||||
|
(an example is provided in the Appendix below).
|
||||||
|
|
||||||
|
"Derivative Works" shall mean any work, whether in Source or Object
|
||||||
|
form, that is based on (or derived from) the Work and for which the
|
||||||
|
editorial revisions, annotations, elaborations, or other modifications
|
||||||
|
represent, as a whole, an original work of authorship. For the purposes
|
||||||
|
of this License, Derivative Works shall not include works that remain
|
||||||
|
separable from, or merely link (or bind by name) to the interfaces of,
|
||||||
|
the Work and Derivative Works thereof.
|
||||||
|
|
||||||
|
"Contribution" shall mean any work of authorship, including
|
||||||
|
the original version of the Work and any modifications or additions
|
||||||
|
to that Work or Derivative Works thereof, that is intentionally
|
||||||
|
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||||
|
or by an individual or Legal Entity authorized to submit on behalf of
|
||||||
|
the copyright owner. For the purposes of this definition, "submitted"
|
||||||
|
means any form of electronic, verbal, or written communication sent
|
||||||
|
to the Licensor or its representatives, including but not limited to
|
||||||
|
communication on electronic mailing lists, source code control systems,
|
||||||
|
and issue tracking systems that are managed by, or on behalf of, the
|
||||||
|
Licensor for the purpose of discussing and improving the Work, but
|
||||||
|
excluding communication that is conspicuously marked or otherwise
|
||||||
|
designated in writing by the copyright owner as "Not a Contribution."
|
||||||
|
|
||||||
|
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||||
|
on behalf of whom a Contribution has been received by Licensor and
|
||||||
|
subsequently incorporated within the Work.
|
||||||
|
|
||||||
|
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||||
|
this License, each Contributor hereby grants to You a perpetual,
|
||||||
|
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||||
|
copyright license to reproduce, prepare Derivative Works of,
|
||||||
|
publicly display, publicly perform, sublicense, and distribute the
|
||||||
|
Work and such Derivative Works in Source or Object form.
|
||||||
|
|
||||||
|
3. Grant of Patent License. Subject to the terms and conditions of
|
||||||
|
this License, each Contributor hereby grants to You a perpetual,
|
||||||
|
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||||
|
(except as stated in this section) patent license to make, have made,
|
||||||
|
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||||
|
where such license applies only to those patent claims licensable
|
||||||
|
by such Contributor that are necessarily infringed by their
|
||||||
|
Contribution(s) alone or by combination of their Contribution(s)
|
||||||
|
with the Work to which such Contribution(s) was submitted. If You
|
||||||
|
institute patent litigation against any entity (including a
|
||||||
|
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||||
|
or a Contribution incorporated within the Work constitutes direct
|
||||||
|
or contributory patent infringement, then any patent licenses
|
||||||
|
granted to You under this License for that Work shall terminate
|
||||||
|
as of the date such litigation is filed.
|
||||||
|
|
||||||
|
4. Redistribution. You may reproduce and distribute copies of the
|
||||||
|
Work or Derivative Works thereof in any medium, with or without
|
||||||
|
modifications, and in Source or Object form, provided that You
|
||||||
|
meet the following conditions:
|
||||||
|
|
||||||
|
(a) You must give any other recipients of the Work or
|
||||||
|
Derivative Works a copy of this License; and
|
||||||
|
|
||||||
|
(b) You must cause any modified files to carry prominent notices
|
||||||
|
stating that You changed the files; and
|
||||||
|
|
||||||
|
(c) You must retain, in the Source form of any Derivative Works
|
||||||
|
that You distribute, all copyright, patent, trademark, and
|
||||||
|
attribution notices from the Source form of the Work,
|
||||||
|
excluding those notices that do not pertain to any part of
|
||||||
|
the Derivative Works; and
|
||||||
|
|
||||||
|
(d) If the Work includes a "NOTICE" text file as part of its
|
||||||
|
distribution, then any Derivative Works that You distribute must
|
||||||
|
include a readable copy of the attribution notices contained
|
||||||
|
within such NOTICE file, excluding those notices that do not
|
||||||
|
pertain to any part of the Derivative Works, in at least one
|
||||||
|
of the following places: within a NOTICE text file distributed
|
||||||
|
as part of the Derivative Works; within the Source form or
|
||||||
|
documentation, if provided along with the Derivative Works; or,
|
||||||
|
within a display generated by the Derivative Works, if and
|
||||||
|
wherever such third-party notices normally appear. The contents
|
||||||
|
of the NOTICE file are for informational purposes only and
|
||||||
|
do not modify the License. You may add Your own attribution
|
||||||
|
notices within Derivative Works that You distribute, alongside
|
||||||
|
or as an addendum to the NOTICE text from the Work, provided
|
||||||
|
that such additional attribution notices cannot be construed
|
||||||
|
as modifying the License.
|
||||||
|
|
||||||
|
You may add Your own copyright statement to Your modifications and
|
||||||
|
may provide additional or different license terms and conditions
|
||||||
|
for use, reproduction, or distribution of Your modifications, or
|
||||||
|
for any such Derivative Works as a whole, provided Your use,
|
||||||
|
reproduction, and distribution of the Work otherwise complies with
|
||||||
|
the conditions stated in this License.
|
||||||
|
|
||||||
|
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||||
|
any Contribution intentionally submitted for inclusion in the Work
|
||||||
|
by You to the Licensor shall be under the terms and conditions of
|
||||||
|
this License, without any additional terms or conditions.
|
||||||
|
Notwithstanding the above, nothing herein shall supersede or modify
|
||||||
|
the terms of any separate license agreement you may have executed
|
||||||
|
with Licensor regarding such Contributions.
|
||||||
|
|
||||||
|
6. Trademarks. This License does not grant permission to use the trade
|
||||||
|
names, trademarks, service marks, or product names of the Licensor,
|
||||||
|
except as required for reasonable and customary use in describing the
|
||||||
|
origin of the Work and reproducing the content of the NOTICE file.
|
||||||
|
|
||||||
|
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||||
|
agreed to in writing, Licensor provides the Work (and each
|
||||||
|
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||||
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||||
|
implied, including, without limitation, any warranties or conditions
|
||||||
|
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||||
|
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||||
|
appropriateness of using or redistributing the Work and assume any
|
||||||
|
risks associated with Your exercise of permissions under this License.
|
||||||
|
|
||||||
|
8. Limitation of Liability. In no event and under no legal theory,
|
||||||
|
whether in tort (including negligence), contract, or otherwise,
|
||||||
|
unless required by applicable law (such as deliberate and grossly
|
||||||
|
negligent acts) or agreed to in writing, shall any Contributor be
|
||||||
|
liable to You for damages, including any direct, indirect, special,
|
||||||
|
incidental, or consequential damages of any character arising as a
|
||||||
|
result of this License or out of the use or inability to use the
|
||||||
|
Work (including but not limited to damages for loss of goodwill,
|
||||||
|
work stoppage, computer failure or malfunction, or any and all
|
||||||
|
other commercial damages or losses), even if such Contributor
|
||||||
|
has been advised of the possibility of such damages.
|
||||||
|
|
||||||
|
9. Accepting Warranty or Additional Liability. While redistributing
|
||||||
|
the Work or Derivative Works thereof, You may choose to offer,
|
||||||
|
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||||
|
or other liability obligations and/or rights consistent with this
|
||||||
|
License. However, in accepting such obligations, You may act only
|
||||||
|
on Your own behalf and on Your sole responsibility, not on behalf
|
||||||
|
of any other Contributor, and only if You agree to indemnify,
|
||||||
|
defend, and hold each Contributor harmless for any liability
|
||||||
|
incurred by, or claims asserted against, such Contributor by reason
|
||||||
|
of your accepting any such warranty or additional liability.
|
||||||
|
|
||||||
|
END OF TERMS AND CONDITIONS
|
||||||
|
|
||||||
|
APPENDIX: How to apply the Apache License to your work.
|
||||||
|
|
||||||
|
To apply the Apache License to your work, attach the following
|
||||||
|
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||||
|
replaced with your own identifying information. (Don't include
|
||||||
|
the brackets!) The text should be enclosed in the appropriate
|
||||||
|
comment syntax for the file format. We also recommend that a
|
||||||
|
file or class name and description of purpose be included on the
|
||||||
|
same "printed page" as the copyright notice for easier
|
||||||
|
identification within third-party archives.
|
||||||
|
|
||||||
|
Copyright 2024 Alibaba Cloud
|
||||||
|
|
||||||
|
Licensed under the Apache License, Version 2.0 (the "License");
|
||||||
|
you may not use this file except in compliance with the License.
|
||||||
|
You may obtain a copy of the License at
|
||||||
|
|
||||||
|
http://www.apache.org/licenses/LICENSE-2.0
|
||||||
|
|
||||||
|
Unless required by applicable law or agreed to in writing, software
|
||||||
|
distributed under the License is distributed on an "AS IS" BASIS,
|
||||||
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||||
|
See the License for the specific language governing permissions and
|
||||||
|
limitations under the License.
|
||||||
93
README.md
Normal file
93
README.md
Normal file
@@ -0,0 +1,93 @@
|
|||||||
|
---
|
||||||
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- multilingual
|
||||||
|
license: apache-2.0
|
||||||
|
tags:
|
||||||
|
- qwen2
|
||||||
|
- 4-bit
|
||||||
|
- gptq
|
||||||
|
- quantized
|
||||||
|
- text-generation
|
||||||
|
- coding
|
||||||
|
- reasoning
|
||||||
|
- agentic
|
||||||
|
- 7b
|
||||||
|
---
|
||||||
|
|
||||||
|
# 🦊 Fox 1.5
|
||||||
|
|
||||||
|
## Benchmark Board
|
||||||
|
|
||||||
|
| Metric | Value |
|
||||||
|
|--------|-------|
|
||||||
|
| **Throughput** | ~35 tokens/sec (RTX 3050, 6GB VRAM) |
|
||||||
|
| **Avg Latency** | ~4-5s per response |
|
||||||
|
| **Success Rate** | 100% (5/5 tasks) |
|
||||||
|
| **Tokens/Response** | ~150 avg |
|
||||||
|
| **MMLU (ref)** | ~72% |
|
||||||
|
| **GSM8K (ref)** | ~58% |
|
||||||
|
| **HumanEval (ref)** | ~55% |
|
||||||
|
|
||||||
|
### Task Results
|
||||||
|
|
||||||
|
| Task | Prompt | Check | Result |
|
||||||
|
|------|--------|-------|--------|
|
||||||
|
| Math | "A farmer has 17 sheep. All but 9 run away. How many sheep left?" | `9` | ✅ |
|
||||||
|
| Coding | "Write a Python function to check if a number is prime." | `def` | ✅ |
|
||||||
|
| Knowledge | "What is the capital of Greece?" | `athens` | ✅ |
|
||||||
|
| Logic | "If all cats are animals and some animals are pets, then some cats are pets. True or false?" | `true` | ✅ |
|
||||||
|
| Translation | "Translate to Greek: Hello, how are you?" | `γεια` | ✅ |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Quick Facts
|
||||||
|
|
||||||
|
| Property | Value |
|
||||||
|
|----------|-------|
|
||||||
|
| Base Model | Qwen2.5-7B-Instruct |
|
||||||
|
| Quantization | GPTQ 4-bit |
|
||||||
|
| Parameters | 7B |
|
||||||
|
| Context Length | 32K tokens |
|
||||||
|
| Size | 5.3GB |
|
||||||
|
| VRAM Required | ~6GB |
|
||||||
|
| License | Apache 2.0 |
|
||||||
|
|
||||||
|
## Capabilities
|
||||||
|
|
||||||
|
- **Text & Chat** — multilingual conversations, creative writing
|
||||||
|
- **Coding** — Python, JavaScript, C++, Rust, Go, 50+ languages
|
||||||
|
- **Reasoning** — math, logic, step-by-step problem solving
|
||||||
|
- **Agentic Use** — tool calling, function execution, OpenClaw compatible
|
||||||
|
|
||||||
|
## Run it
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
|
||||||
|
model_name = "teolm30/Fox-1.5"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_name,
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
messages = [{"role": "user", "content": "Explain quantum entanglement in simple terms"}]
|
||||||
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||||
|
inputs = tokenizer(text, return_tensors="pt").to("cuda:0")
|
||||||
|
outputs = model.generate(**inputs, max_new_tokens=512)
|
||||||
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||||
|
```
|
||||||
|
|
||||||
|
For 4-bit GPTQ loading: `pip install auto-gptq optimum`
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
- Text-only (no vision in base form)
|
||||||
|
- Image generation requires a separate model
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
*Built by T_craftClaw 🔥 | Owner: teolm30*
|
||||||
51
config.json
Normal file
51
config.json
Normal file
@@ -0,0 +1,51 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3584,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 18944,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 28,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 4,
|
||||||
|
"quantization_config": {
|
||||||
|
"batch_size": 1,
|
||||||
|
"bits": 4,
|
||||||
|
"block_name_to_quantize": null,
|
||||||
|
"cache_block_outputs": true,
|
||||||
|
"damp_percent": 0.01,
|
||||||
|
"dataset": null,
|
||||||
|
"desc_act": false,
|
||||||
|
"exllama_config": {
|
||||||
|
"version": 1
|
||||||
|
},
|
||||||
|
"group_size": 128,
|
||||||
|
"max_input_length": null,
|
||||||
|
"model_seqlen": null,
|
||||||
|
"module_name_preceding_first_block": null,
|
||||||
|
"modules_in_block_to_quantize": null,
|
||||||
|
"pad_token_id": null,
|
||||||
|
"quant_method": "gptq",
|
||||||
|
"sym": true,
|
||||||
|
"tokenizer": null,
|
||||||
|
"true_sequential": true,
|
||||||
|
"use_cuda_fp16": false,
|
||||||
|
"use_exllama": true
|
||||||
|
},
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 131072,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.39.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 152064
|
||||||
|
}
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"repetition_penalty": 1.05,
|
||||||
|
"temperature": 0.7,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.8,
|
||||||
|
"transformers_version": "4.39.3"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
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 sha256:278698de6ca93314e68edf14f57fe14af9fb4255034f06d4eb8272671b4973d2
|
||||||
|
size 3999234216
|
||||||
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 sha256:77b6cb5d6c191b97a8afa9a19092db693db41068241cf27c7c67cedb096e9664
|
||||||
|
size 1576146928
|
||||||
934
model.safetensors.index.json
Normal file
934
model.safetensors.index.json
Normal file
@@ -0,0 +1,934 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 5575277568
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00002-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.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||||
|
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
303282
tokenizer.json
Normal file
303282
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user