初始化项目，由ModelHub XC社区提供模型
Model: LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
178
README.md
Normal file
178
README.md
Normal file
@@ -0,0 +1,178 @@
|
||||
---
|
||||
base_model:
|
||||
- groxaxo/MagiSeek-Pro-V1
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- quantized
|
||||
- w4a16
|
||||
- tuning
|
||||
- low-bit-open-llm-leaderboard
|
||||
---
|
||||
|
||||
# MagiSeek-Pro-V1-AutoRound-W4A16-Tuning
|
||||
|
||||
## Model Details
|
||||
|
||||
This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of [groxaxo/MagiSeek-Pro-V1](https://huggingface.co/groxaxo/MagiSeek-Pro-V1) generated by TUNING. Please follow the license of the original model.
|
||||
|
||||
## Quantization Details
|
||||
|
||||
| Attribute | Value |
|
||||
|-----------|-------|
|
||||
| Base Model | [groxaxo/MagiSeek-Pro-V1](https://huggingface.co/groxaxo/MagiSeek-Pro-V1) |
|
||||
| Quantization Tool | TUNING |
|
||||
| Quantization Scheme | W4A16 |
|
||||
| Quantized Size | 13575 MB |
|
||||
|
||||
## Evaluation Results
|
||||
|
||||
| Task | Accuracy |
|
||||
|------|----------|
|
||||
| hellaswag | 0.6212 |
|
||||
| mmlu | 0.7433 |
|
||||
| mmlu_abstract_algebra | 0.4600 |
|
||||
| mmlu_anatomy | 0.8074 |
|
||||
| mmlu_astronomy | 0.8882 |
|
||||
| mmlu_business_ethics | 0.7600 |
|
||||
| mmlu_clinical_knowledge | 0.8151 |
|
||||
| mmlu_college_biology | 0.8819 |
|
||||
| mmlu_college_chemistry | 0.5400 |
|
||||
| mmlu_college_computer_science | 0.7200 |
|
||||
| mmlu_college_mathematics | 0.4900 |
|
||||
| mmlu_college_medicine | 0.7457 |
|
||||
| mmlu_college_physics | 0.6569 |
|
||||
| mmlu_computer_security | 0.7900 |
|
||||
| mmlu_conceptual_physics | 0.7745 |
|
||||
| mmlu_econometrics | 0.5965 |
|
||||
| mmlu_electrical_engineering | 0.7379 |
|
||||
| mmlu_elementary_mathematics | 0.7434 |
|
||||
| mmlu_formal_logic | 0.4603 |
|
||||
| mmlu_global_facts | 0.5700 |
|
||||
| mmlu_high_school_biology | 0.8871 |
|
||||
| mmlu_high_school_chemistry | 0.7241 |
|
||||
| mmlu_high_school_computer_science | 0.8600 |
|
||||
| mmlu_high_school_european_history | 0.8242 |
|
||||
| mmlu_high_school_geography | 0.8838 |
|
||||
| mmlu_high_school_government_and_politics | 0.9689 |
|
||||
| mmlu_high_school_macroeconomics | 0.7846 |
|
||||
| mmlu_high_school_mathematics | 0.4926 |
|
||||
| mmlu_high_school_microeconomics | 0.8403 |
|
||||
| mmlu_high_school_physics | 0.5894 |
|
||||
| mmlu_high_school_psychology | 0.9174 |
|
||||
| mmlu_high_school_statistics | 0.6944 |
|
||||
| mmlu_high_school_us_history | 0.8971 |
|
||||
| mmlu_high_school_world_history | 0.8692 |
|
||||
| mmlu_human_aging | 0.7982 |
|
||||
| mmlu_human_sexuality | 0.8779 |
|
||||
| mmlu_humanities | 0.6536 |
|
||||
| mmlu_international_law | 0.8430 |
|
||||
| mmlu_jurisprudence | 0.8241 |
|
||||
| mmlu_logical_fallacies | 0.8589 |
|
||||
| mmlu_machine_learning | 0.5804 |
|
||||
| mmlu_management | 0.8835 |
|
||||
| mmlu_marketing | 0.9444 |
|
||||
| mmlu_medical_genetics | 0.8600 |
|
||||
| mmlu_miscellaneous | 0.8991 |
|
||||
| mmlu_moral_disputes | 0.7688 |
|
||||
| mmlu_moral_scenarios | 0.4290 |
|
||||
| mmlu_nutrition | 0.8562 |
|
||||
| mmlu_other | 0.8069 |
|
||||
| mmlu_philosophy | 0.7588 |
|
||||
| mmlu_prehistory | 0.8364 |
|
||||
| mmlu_professional_accounting | 0.6064 |
|
||||
| mmlu_professional_law | 0.5587 |
|
||||
| mmlu_professional_medicine | 0.8125 |
|
||||
| mmlu_professional_psychology | 0.8007 |
|
||||
| mmlu_public_relations | 0.7818 |
|
||||
| mmlu_security_studies | 0.8408 |
|
||||
| mmlu_social_sciences | 0.8460 |
|
||||
| mmlu_sociology | 0.8905 |
|
||||
| mmlu_stem | 0.7146 |
|
||||
| mmlu_us_foreign_policy | 0.9100 |
|
||||
| mmlu_virology | 0.5723 |
|
||||
| mmlu_world_religions | 0.8596 |
|
||||
| piqa | 0.8183 |
|
||||
|
||||
## How to Use
|
||||
|
||||
### HF Usage
|
||||
|
||||
**Step 1: Install [AutoRound](https://github.com/intel/auto-round)**
|
||||
|
||||
```bash
|
||||
pip install auto-round
|
||||
```
|
||||
|
||||
**Step 2: Load and run the quantized model**
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "MagiSeek-Pro-V1-AutoRound-W4A16-Tuning"
|
||||
|
||||
# load the tokenizer and the model
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
|
||||
|
||||
# prepare the model input
|
||||
prompt = "Write a quick sort algorithm."
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
|
||||
# conduct text completion
|
||||
generated_ids = model.generate(**model_inputs, max_new_tokens=512)
|
||||
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist()
|
||||
|
||||
content = tokenizer.decode(output_ids, skip_special_tokens=True)
|
||||
print("content:", content)
|
||||
```
|
||||
|
||||
### VLLM Usage
|
||||
|
||||
```bash
|
||||
vllm serve MagiSeek-Pro-V1-AutoRound-W4A16-Tuning \
|
||||
--trust-remote-code \
|
||||
--dtype bfloat16 \
|
||||
--tensor_parallel_size 1
|
||||
```
|
||||
|
||||
If you encounter any issues, feel free to open an issue on the [AutoRound GitHub repo](https://github.com/intel/auto-round/issues) or provide feedback on the [Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard).
|
||||
|
||||
## Ethical Considerations and Limitations
|
||||
|
||||
The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
|
||||
Therefore, before deploying any applications of the model, developers should perform safety testing.
|
||||
|
||||
## Caveats and Recommendations
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
|
||||
Here are a couple of useful links to learn more about Intel's AI software:
|
||||
|
||||
- [Intel Neural Compressor](https://github.com/intel/neural-compressor)
|
||||
- [AutoRound](https://github.com/intel/auto-round)
|
||||
|
||||
## Disclaimer
|
||||
|
||||
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
|
||||
|
||||
## Cite
|
||||
|
||||
```
|
||||
@article{cheng2023optimize,
|
||||
title={Optimize weight rounding via signed gradient descent for the quantization of llms},
|
||||
author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi},
|
||||
journal={arXiv preprint arXiv:2309.05516},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
|
||||
[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
|
||||
|
||||
---
|
||||
|
||||
*This model is part of the [Intel Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard) initiative.*
|
||||
48
chat_template.jinja
Normal file
48
chat_template.jinja
Normal file
@@ -0,0 +1,48 @@
|
||||
{# Magidonia p5 OpenCode bridge: model-native <tool_call> JSON protocol. #}
|
||||
{{- bos_token }}
|
||||
{%- if messages and messages[0]['role'] == 'system' %}
|
||||
{%- set raw_system = messages[0]['content'] if messages[0]['content'] is string else messages[0]['content'][0]['text'] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set raw_system = '' %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{%- if raw_system|length > 0 %}
|
||||
{{- '[SYSTEM_PROMPT]' + raw_system + '[/SYSTEM_PROMPT]' }}
|
||||
{%- endif %}
|
||||
{%- if tools is defined and tools is not none and tools|length > 0 %}
|
||||
{{- '[AVAILABLE_TOOLS]' + (tools | tojson) + '[/AVAILABLE_TOOLS]' }}
|
||||
{%- endif %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message['role'] == 'user' %}
|
||||
{{- '[INST]' }}
|
||||
{%- if message['content'] is string %}
|
||||
{{- message['content'] }}
|
||||
{%- else %}
|
||||
{%- for block in message['content'] %}
|
||||
{%- if block['type'] == 'text' %}{{- block['text'] if block['text'] is defined else block['content'] }}
|
||||
{%- elif block['type'] in ['image', 'image_url'] %}{{- '[IMG]' }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '[/INST]' }}
|
||||
{%- elif message['role'] == 'assistant' %}
|
||||
{%- if message['reasoning_content'] is defined and message['reasoning_content'] is not none %}
|
||||
{{- '<thinking>' + message['reasoning_content'] + '</thinking>' }}
|
||||
{%- endif %}
|
||||
{%- if message['content'] is string %}{{- message['content'] }}
|
||||
{%- elif message['content'] is iterable %}{{- message['content'][0]['text'] }}
|
||||
{%- endif %}
|
||||
{%- if message['tool_calls'] is defined and message['tool_calls'] is not none %}
|
||||
{%- for tool in message['tool_calls'] %}
|
||||
{%- set args = tool['function']['arguments'] %}
|
||||
{%- if args is not string %}{%- set args = args|tojson %}{%- endif %}
|
||||
{{- '<tool_call>{"name":"' + tool['function']['name'] + '","arguments":' + args + '}</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- eos_token }}
|
||||
{%- elif message['role'] == 'tool' or message['role'] == 'tool_results' %}
|
||||
{%- set result = message['content']['content'] if message['content'] is mapping and message['content']['content'] is defined else message['content'] %}
|
||||
{{- '[TOOL_RESULTS]' + result|string + '[/TOOL_RESULTS]' + eos_token }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
42
config.json
Normal file
42
config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 11,
|
||||
"quantization_config": {
|
||||
"autoround_version": "0.14.2",
|
||||
"bits": 4,
|
||||
"block_name_to_quantize": "model.layers",
|
||||
"data_type": "int",
|
||||
"group_size": 128,
|
||||
"low_gpu_mem_usage": true,
|
||||
"packing_format": "auto_round:auto_gptq",
|
||||
"quant_method": "auto-round",
|
||||
"sym": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.14.1",
|
||||
"unsloth_version": "2025.12.5",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 11,
|
||||
"transformers_version": "5.14.1",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb3def3ada979017fdd9c006a49c9142dec57e9fe3d551a4bc7389fb098abea2
|
||||
size 4994366080
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4a3b78988eb35215238dd55c30d3055e5ae6ae82b6ad11cad383081c599e22d
|
||||
size 4995915688
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12dfb53b29b5a4f19e79fd37c6753edecc0d4db8efdf70f280f6f189ed4873b4
|
||||
size 4244088968
|
||||
931
model.safetensors.index.json
Normal file
931
model.safetensors.index.json
Normal file
@@ -0,0 +1,931 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 1342592000,
|
||||
"total_size": 14234265600
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
11
quantization_config.json
Normal file
11
quantization_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"bits": 4,
|
||||
"data_type": "int",
|
||||
"group_size": 128,
|
||||
"sym": true,
|
||||
"low_gpu_mem_usage": true,
|
||||
"autoround_version": "0.14.2",
|
||||
"block_name_to_quantize": "model.layers",
|
||||
"quant_method": "auto-round",
|
||||
"packing_format": "auto_round:auto_gptq"
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:158915c7c928301e0d32f1da363e45c294d907bd4c64a8e855f0bd1a47b9e870
|
||||
size 17078001
|
||||
18
tokenizer_config.json
Normal file
18
tokenizer_config.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"add_prefix_space": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"is_local": false,
|
||||
"legacy": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<pad>",
|
||||
"padding_side": "left",
|
||||
"processor_class": "PixtralProcessor",
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user