commit 1e10aca7ba54e6b31985cdeba1ce43e6f491f94a Author: ModelHub XC Date: Fri May 1 06:38:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: TheBloke/Nous-Capybara-34B-AWQ Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..48c67b2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..92bb5e0 --- /dev/null +++ b/README.md @@ -0,0 +1,448 @@ +--- +base_model: NousResearch/Nous-Capybara-34B +datasets: +- LDJnr/LessWrong-Amplify-Instruct +- LDJnr/Pure-Dove +- LDJnr/Verified-Camel +inference: false +language: +- eng +license: +- mit +model_creator: NousResearch +model_name: Nous Capybara 34B +model_type: yi +prompt_template: 'USER: {prompt} ASSISTANT:' +quantized_by: TheBloke +tags: +- sft +- StableLM +--- + + + + +
+TheBlokeAI +
+
+
+

Chat & support: TheBloke's Discord server

+
+
+

Want to contribute? TheBloke's Patreon page

+
+
+

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

+
+ + +# Nous Capybara 34B - AWQ +- Model creator: [NousResearch](https://huggingface.co/NousResearch) +- Original model: [Nous Capybara 34B](https://huggingface.co/NousResearch/Nous-Capybara-34B) + + +## Description + +This repo contains AWQ model files for [NousResearch's Nous Capybara 34B](https://huggingface.co/NousResearch/Nous-Capybara-34B). + +These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/). + + +### About AWQ + +AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. + +It is supported by: + +- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ +- [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only +- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) +- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers +- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code + + + +## Repositories available + +* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Nous-Capybara-34B-AWQ) +* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Nous-Capybara-34B-GPTQ) +* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Nous-Capybara-34B-GGUF) +* [NousResearch's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Nous-Capybara-34B) + + + +## Prompt template: User-Assistant + +```USER: {prompt} ASSISTANT:``` + + + + + +## Provided files, and AWQ parameters + +I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered. + +Models are released as sharded safetensors files. + +| Branch | Bits | GS | AWQ Dataset | Seq Len | Size | +| ------ | ---- | -- | ----------- | ------- | ---- | +| [main](https://huggingface.co/TheBloke/Nous-Capybara-34B-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 19.23 GB + + + + +## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui) + +Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). + +It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. + +1. Click the **Model tab**. +2. Under **Download custom model or LoRA**, enter `TheBloke/Nous-Capybara-34B-AWQ`. +3. Click **Download**. +4. The model will start downloading. Once it's finished it will say "Done". +5. In the top left, click the refresh icon next to **Model**. +6. In the **Model** dropdown, choose the model you just downloaded: `Nous-Capybara-34B-AWQ` +7. Select **Loader: AutoAWQ**. +8. Click Load, and the model will load and is now ready for use. +9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right. +10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started! + + + +## Multi-user inference server: vLLM + +Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/). + +- Please ensure you are using vLLM version 0.2 or later. +- When using vLLM as a server, pass the `--quantization awq` parameter. + +For example: + +```shell +python3 -m vllm.entrypoints.api_server --model TheBloke/Nous-Capybara-34B-AWQ --quantization awq --dtype auto +``` + +- When using vLLM from Python code, again set `quantization=awq`. + +For example: + +```python +from vllm import LLM, SamplingParams + +prompts = [ + "Tell me about AI", + "Write a story about llamas", + "What is 291 - 150?", + "How much wood would a woodchuck chuck if a woodchuck could chuck wood?", +] +prompt_template=f'''USER: {prompt} +ASSISTANT: +''' + +prompts = [prompt_template.format(prompt=prompt) for prompt in prompts] + +sampling_params = SamplingParams(temperature=0.8, top_p=0.95) + +llm = LLM(model="TheBloke/Nous-Capybara-34B-AWQ", quantization="awq", dtype="auto") + +outputs = llm.generate(prompts, sampling_params) + +# Print the outputs. +for output in outputs: + prompt = output.prompt + generated_text = output.outputs[0].text + print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}") +``` + + + +## Multi-user inference server: Hugging Face Text Generation Inference (TGI) + +Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0` + +Example Docker parameters: + +```shell +--model-id TheBloke/Nous-Capybara-34B-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 +``` + +Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later): + +```shell +pip3 install huggingface-hub +``` + +```python +from huggingface_hub import InferenceClient + +endpoint_url = "https://your-endpoint-url-here" + +prompt = "Tell me about AI" +prompt_template=f'''USER: {prompt} +ASSISTANT: +''' + +client = InferenceClient(endpoint_url) +response = client.text_generation(prompt, + max_new_tokens=128, + do_sample=True, + temperature=0.7, + top_p=0.95, + top_k=40, + repetition_penalty=1.1) + +print(f"Model output: ", response) +``` + + + +## Inference from Python code using Transformers + +### Install the necessary packages + +- Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later. +- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later. + +```shell +pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0" +``` + +Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0. + +If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command: + +```shell +pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl +``` + +If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead: + +```shell +pip3 uninstall -y autoawq +git clone https://github.com/casper-hansen/AutoAWQ +cd AutoAWQ +pip3 install . +``` + +### Transformers example code (requires Transformers 4.35.0 and later) + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer + +model_name_or_path = "TheBloke/Nous-Capybara-34B-AWQ" + +tokenizer = AutoTokenizer.from_pretrained(model_name_or_path) +model = AutoModelForCausalLM.from_pretrained( + model_name_or_path, + low_cpu_mem_usage=True, + device_map="cuda:0" +) + +# Using the text streamer to stream output one token at a time +streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) + +prompt = "Tell me about AI" +prompt_template=f'''USER: {prompt} +ASSISTANT: +''' + +# Convert prompt to tokens +tokens = tokenizer( + prompt_template, + return_tensors='pt' +).input_ids.cuda() + +generation_params = { + "do_sample": True, + "temperature": 0.7, + "top_p": 0.95, + "top_k": 40, + "max_new_tokens": 512, + "repetition_penalty": 1.1 +} + +# Generate streamed output, visible one token at a time +generation_output = model.generate( + tokens, + streamer=streamer, + **generation_params +) + +# Generation without a streamer, which will include the prompt in the output +generation_output = model.generate( + tokens, + **generation_params +) + +# Get the tokens from the output, decode them, print them +token_output = generation_output[0] +text_output = tokenizer.decode(token_output) +print("model.generate output: ", text_output) + +# Inference is also possible via Transformers' pipeline +from transformers import pipeline + +pipe = pipeline( + "text-generation", + model=model, + tokenizer=tokenizer, + **generation_params +) + +pipe_output = pipe(prompt_template)[0]['generated_text'] +print("pipeline output: ", pipe_output) + +``` + + + +## Compatibility + +The files provided are tested to work with: + +- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`. +- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later. +- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later. +- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later. +- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later. + + + + + +## Discord + +For further support, and discussions on these models and AI in general, join us at: + +[TheBloke AI's Discord server](https://discord.gg/theblokeai) + +## Thanks, and how to contribute + +Thanks to the [chirper.ai](https://chirper.ai) team! + +Thanks to Clay from [gpus.llm-utils.org](llm-utils)! + +I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. + +If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. + +Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. + +* Patreon: https://patreon.com/TheBlokeAI +* Ko-Fi: https://ko-fi.com/TheBlokeAI + +**Special thanks to**: Aemon Algiz. + +**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius + + +Thank you to all my generous patrons and donaters! + +And thank you again to a16z for their generous grant. + + + +# Original model card: NousResearch's Nous Capybara 34B + + +## **Nous-Capybara-34B V1.9** + +**This is trained on the Yi-34B model with 200K context length, for 3 epochs on the Capybara dataset!** + +**First 34B Nous model and first 200K context length Nous model!** + +The Capybara series is the first Nous collection of models made by fine-tuning mostly on data created by Nous in-house. + +We leverage our novel data synthesis technique called Amplify-instruct (Paper coming soon), the seed distribution and synthesis method are comprised of a synergistic combination of top performing existing data synthesis techniques and distributions used for SOTA models such as Airoboros, Evol-Instruct(WizardLM), Orca, Vicuna, Know_Logic, Lamini, FLASK and others, all into one lean holistically formed methodology for the dataset and model. The seed instructions used for the start of synthesized conversations are largely based on highly datasets like Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from posts on the website LessWrong, as well as being supplemented with certain in-house multi-turn datasets like Dove(A successor to Puffin). + +While performing great in it's current state, the current dataset used for fine-tuning is entirely contained within 20K training examples, this is 10 times smaller than many similar performing current models, this is signficant when it comes to scaling implications for our next generation of models once we scale our novel syntheiss methods to significantly more examples. + +## Process of creation and special thank yous! + +This model was fine-tuned by Nous Research as part of the Capybara/Amplify-Instruct project led by Luigi D.(LDJ) (Paper coming soon), as well as significant dataset formation contributions by J-Supha and general compute and experimentation management by Jeffrey Q. during ablations. + +Special thank you to **A16Z** for sponsoring our training, as well as **Yield Protocol** for their support in financially sponsoring resources during the R&D of this project. + +## Thank you to those of you that have indirectly contributed! + +While most of the tokens within Capybara are newly synthsized and part of datasets like Puffin/Dove, we would like to credit the single-turn datasets we leveraged as seeds that are used to generate the multi-turn data as part of the Amplify-Instruct synthesis. + +The datasets shown in green below are datasets that we sampled from to curate seeds that are used during Amplify-Instruct synthesis for this project. + +Datasets in Blue are in-house curations that previously existed prior to Capybara. + +![Capybara](https://i.imgur.com/yB58OoD.jpeg) + + +## Prompt Format + +The reccomended model usage is: + +``` +USER: + +ASSISTANT: +``` + +## Mutli-Modality! + + - We currently have a Multi-modal model based on Capybara V1.9! +https://huggingface.co/NousResearch/Obsidian-3B-V0.5 +it is currently only available as a 3B sized model but larger versions coming! + + +## Notable Features: + + - Uses Yi-34B model as the base which is trained for 200K context length! + + - Over 60% of the dataset is comprised of multi-turn conversations.(Most models are still only trained for single-turn conversations and no back and forths!) + + - Over 1,000 tokens average per conversation example! (Most models are trained on conversation data that is less than 300 tokens per example.) + + - Able to effectively do complex summaries of advanced topics and studies. (trained on hundreds of advanced difficult summary tasks developed in-house) + + - Ability to recall information upto late 2022 without internet. + + - Includes a portion of conversational data synthesized from less wrong posts, discussing very in-depth details and philosophies about the nature of reality, reasoning, rationality, self-improvement and related concepts. + +## Example Outputs from Capybara V1.9 7B version! (examples from 34B coming soon): + +![Capybara](https://img001.prntscr.com/file/img001/T9yYxR1xQSaK_UGdy3t2Cw.png) + +![Capybara](https://img001.prntscr.com/file/img001/DQXqmKbsQQOIcgny1eoGNA.png) + +![Capybara](https://img001.prntscr.com/file/img001/85X3L9ZxTsOKo3fUQ7GRVA.png) + +## Benchmarks! (Coming soon!) + + +## Future model sizes + +Capybara V1.9 now currently has a 3B, 7B and 34B size, and we plan to eventually have a 13B and 70B version in the future, as well as a potential 1B version based on phi-1.5 or Tiny Llama. + +## How you can help! + +In the near future we plan on leveraging the help of domain specific expert volunteers to eliminate any mathematically/verifiably incorrect answers from our training curations. + +If you have at-least a bachelors in mathematics, physics, biology or chemistry and would like to volunteer even just 30 minutes of your expertise time, please contact LDJ on discord! + +## Dataset contamination. + +We have checked the capybara dataset for contamination for several of the most popular datasets and can confirm that there is no contaminaton found. + +We leveraged minhash to check for 100%, 99%, 98% and 97% similarity matches between our data and the questions and answers in benchmarks, we found no exact matches, nor did we find any matches down to the 97% similarity level. + +The following are benchmarks we checked for contamination against our dataset: + +- HumanEval + +- AGIEval + +- TruthfulQA + +- MMLU + +- GPT4All diff --git a/config.json b/config.json new file mode 100644 index 0000000..ff545a5 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "_name_or_path": "/workspace/process/nousresearch_nous-capybara-34b/source", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 7168, + "initializer_range": 0.02, + "intermediate_size": 20480, + "max_position_embeddings": 200000, + "model_type": "llama", + "num_attention_heads": 56, + "num_hidden_layers": 60, + "num_key_value_heads": 8, + "pad_token_id": 0, + "pretraining_tp": 1, + "quantization_config": { + "bits": 4, + "group_size": 128, + "quant_method": "awq", + "version": "gemm", + "zero_point": true + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.35.0", + "use_cache": true, + "vocab_size": 64000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c26d216 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.34.1" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..ddd326b --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1e93df938dbbf1420c9172a329d2e54b2b6b38de0aa434ccc2a037364fa9f2 +size 9963803400 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..d6ae6b8 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da618bb376b53250aeb9435ed4411a01f9a2e11e26e70f6e6853d3d6c8dfb03b +size 9262091504 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d49f666 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1390 @@ +{ + "metadata": { + "total_size": 19225737216 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.48.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.48.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.49.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.50.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.51.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.52.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.53.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.54.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.55.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.56.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.57.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.58.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.59.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors", + "lm_head.weight": "model-00002-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/quant_config.json b/quant_config.json new file mode 100644 index 0000000..01a8401 --- /dev/null +++ b/quant_config.json @@ -0,0 +1,6 @@ +{ + "zero_point": true, + "q_group_size": 128, + "w_bit": 4, + "version": "GEMM" +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..335ae1c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenization_yi.py b/tokenization_yi.py new file mode 100644 index 0000000..bb82053 --- /dev/null +++ b/tokenization_yi.py @@ -0,0 +1,255 @@ +import os +from shutil import copyfile +from typing import Any, Dict, List, Optional, Tuple + +import sentencepiece as spm +from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer +from transformers.utils import logging + +logger = logging.get_logger(__name__) + +VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"} + +PRETRAINED_VOCAB_FILES_MAP = { + "vocab_file": {}, + "tokenizer_file": {}, +} +PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {} + + +class YiTokenizer(PreTrainedTokenizer): + """ + Construct a Yi tokenizer. Based on byte-level Byte-Pair-Encoding. + + Args: + vocab_file (`str`): + Path to the vocabulary file. + """ + + vocab_files_names = VOCAB_FILES_NAMES + pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP + max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES + model_input_names = ["input_ids", "attention_mask"] + + def __init__( + self, + vocab_file, + unk_token="", + bos_token="<|startoftext|>", + eos_token="<|endoftext|>", + pad_token="", + sp_model_kwargs: Optional[Dict[str, Any]] = None, + add_bos_token=True, + add_eos_token=False, + clean_up_tokenization_spaces=False, + **kwargs, + ): + self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs + bos_token = ( + AddedToken(bos_token, lstrip=False, rstrip=False) + if isinstance(bos_token, str) + else bos_token + ) + eos_token = ( + AddedToken(eos_token, lstrip=False, rstrip=False) + if isinstance(eos_token, str) + else eos_token + ) + unk_token = ( + AddedToken(unk_token, lstrip=False, rstrip=False) + if isinstance(unk_token, str) + else unk_token + ) + pad_token = ( + AddedToken(pad_token, lstrip=False, rstrip=False) + if isinstance(pad_token, str) + else pad_token + ) + self.vocab_file = vocab_file + self.add_bos_token = add_bos_token + self.add_eos_token = add_eos_token + self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) + self.sp_model.Load(vocab_file) + super().__init__( + bos_token=bos_token, + eos_token=eos_token, + unk_token=unk_token, + pad_token=pad_token, + add_bos_token=add_bos_token, + add_eos_token=add_eos_token, + sp_model_kwargs=self.sp_model_kwargs, + clean_up_tokenization_spaces=clean_up_tokenization_spaces, + **kwargs, + ) + + def __getstate__(self): + state = self.__dict__.copy() + state["sp_model"] = None + return state + + def __setstate__(self, d): + self.__dict__ = d + self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) + self.sp_model.Load(self.vocab_file) + + @property + def vocab_size(self): + """Returns vocab size""" + return self.sp_model.get_piece_size() + + def get_vocab(self): + """Returns vocab as a dict""" + vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)} + vocab.update(self.added_tokens_encoder) + return vocab + + def _tokenize(self, text): + """Returns a tokenized string.""" + return self.sp_model.encode(text, out_type=str) + + def _convert_token_to_id(self, token): + """Converts a token (str) in an id using the vocab.""" + return self.sp_model.piece_to_id(token) + + def _convert_id_to_token(self, index): + """Converts an index (integer) in a token (str) using the vocab.""" + token = self.sp_model.IdToPiece(index) + return token + + def convert_tokens_to_string(self, tokens): + """Converts a sequence of tokens (string) in a single string.""" + current_sub_tokens = [] + out_string = "" + prev_is_special = False + for i, token in enumerate(tokens): + # make sure that special tokens are not decoded using sentencepiece model + if token in self.all_special_tokens: + if not prev_is_special and i != 0: + out_string += " " + out_string += self.sp_model.decode(current_sub_tokens) + token + prev_is_special = True + current_sub_tokens = [] + else: + current_sub_tokens.append(token) + prev_is_special = False + out_string += self.sp_model.decode(current_sub_tokens) + return out_string + + def save_vocabulary( + self, save_directory, filename_prefix: Optional[str] = None + ) -> Tuple[str]: + """ + Save the vocabulary and special tokens file to a directory. + + Args: + save_directory (`str`): + The directory in which to save the vocabulary. + + Returns: + `Tuple(str)`: Paths to the files saved. + """ + if not os.path.isdir(save_directory): + logger.error(f"Vocabulary path ({save_directory}) should be a directory") + return + out_vocab_file = os.path.join( + save_directory, + (filename_prefix + "-" if filename_prefix else "") + + VOCAB_FILES_NAMES["vocab_file"], + ) + + if os.path.abspath(self.vocab_file) != os.path.abspath( + out_vocab_file + ) and os.path.isfile(self.vocab_file): + copyfile(self.vocab_file, out_vocab_file) + elif not os.path.isfile(self.vocab_file): + with open(out_vocab_file, "wb") as fi: + content_spiece_model = self.sp_model.serialized_model_proto() + fi.write(content_spiece_model) + + return (out_vocab_file,) + + def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None): + bos_token_id = [self.bos_token_id] if self.add_bos_token else [] + eos_token_id = [self.eos_token_id] if self.add_eos_token else [] + + output = bos_token_id + token_ids_0 + eos_token_id + + if token_ids_1 is not None: + output = output + bos_token_id + token_ids_1 + eos_token_id + + return output + + def get_special_tokens_mask( + self, + token_ids_0: List[int], + token_ids_1: Optional[List[int]] = None, + already_has_special_tokens: bool = False, + ) -> List[int]: + """ + Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding + special tokens using the tokenizer `prepare_for_model` method. + + Args: + token_ids_0 (`List[int]`): + List of IDs. + token_ids_1 (`List[int]`, *optional*): + Optional second list of IDs for sequence pairs. + already_has_special_tokens (`bool`, *optional*, defaults to `False`): + Whether or not the token list is already formatted with special tokens for the model. + + Returns: + `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. + """ + if already_has_special_tokens: + return super().get_special_tokens_mask( + token_ids_0=token_ids_0, + token_ids_1=token_ids_1, + already_has_special_tokens=True, + ) + + bos_token_id = [1] if self.add_bos_token else [] + eos_token_id = [1] if self.add_eos_token else [] + + if token_ids_1 is None: + return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id + return ( + bos_token_id + + ([0] * len(token_ids_0)) + + eos_token_id + + bos_token_id + + ([0] * len(token_ids_1)) + + eos_token_id + ) + + def create_token_type_ids_from_sequences( + self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None + ) -> List[int]: + """ + Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT + sequence pair mask has the following format: + + ``` + 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 + | first sequence | second sequence | + ``` + + if token_ids_1 is None, only returns the first portion of the mask (0s). + + Args: + token_ids_0 (`List[int]`): + List of ids. + token_ids_1 (`List[int]`, *optional*): + Optional second list of IDs for sequence pairs. + + Returns: + `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s). + """ + bos_token_id = [self.bos_token_id] if self.add_bos_token else [] + eos_token_id = [self.eos_token_id] if self.add_eos_token else [] + + output = [0] * len(bos_token_id + token_ids_0 + eos_token_id) + + if token_ids_1 is not None: + output += [1] * len(bos_token_id + token_ids_1 + eos_token_id) + + return output diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8306c82 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39 +size 1033105 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b67a471 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "auto_map": { + "AutoTokenizer": [ + "tokenization_yi.YiTokenizer", + null + ] + }, + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "model_max_length": 200000, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "YiTokenizer", + "unk_token": "" +}