From be4275de08799ce65896896bd758bb9aff6502bb Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 22 May 2026 12:37:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: DuoNeural/Archon-R1-32B Source: Original Platform --- .gitattributes | 36 ++ README.md | 167 +++++++ abliteration_meta.json | 15 + chat_template.jinja | 1 + config.json | 97 ++++ generation_config.json | 9 + model-00001-of-00014.safetensors | 3 + model-00002-of-00014.safetensors | 3 + model-00003-of-00014.safetensors | 3 + model-00004-of-00014.safetensors | 3 + model-00005-of-00014.safetensors | 3 + model-00006-of-00014.safetensors | 3 + model-00007-of-00014.safetensors | 3 + model-00008-of-00014.safetensors | 3 + model-00009-of-00014.safetensors | 3 + model-00010-of-00014.safetensors | 3 + model-00011-of-00014.safetensors | 3 + model-00012-of-00014.safetensors | 3 + model-00013-of-00014.safetensors | 3 + model-00014-of-00014.safetensors | 3 + model.safetensors.index.json | 779 +++++++++++++++++++++++++++++++ tokenizer.json | 3 + tokenizer_config.json | 15 + 23 files changed, 1164 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 abliteration_meta.json create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00014.safetensors create mode 100644 model-00002-of-00014.safetensors create mode 100644 model-00003-of-00014.safetensors create mode 100644 model-00004-of-00014.safetensors create mode 100644 model-00005-of-00014.safetensors create mode 100644 model-00006-of-00014.safetensors create mode 100644 model-00007-of-00014.safetensors create mode 100644 model-00008-of-00014.safetensors create mode 100644 model-00009-of-00014.safetensors create mode 100644 model-00010-of-00014.safetensors create mode 100644 model-00011-of-00014.safetensors create mode 100644 model-00012-of-00014.safetensors create mode 100644 model-00013-of-00014.safetensors create mode 100644 model-00014-of-00014.safetensors create mode 100644 model.safetensors.index.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1dd28d9 --- /dev/null +++ b/README.md @@ -0,0 +1,167 @@ +--- +language: +- en +- zh +- fr +- de +- es +- ja +- ko +tags: +- deepseek +- deepseek-r1 +- reasoning +- abliteration +- uncensored +- text-generation +- chain-of-thought +license: mit +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B +pipeline_tag: text-generation +--- + +# Archon-R1-32B + +**Base:** `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` | **License:** MIT | **Method:** SVD refusal direction abliteration + +R1-level reasoning. No safety conditioning. + +## What this is + +DeepSeek-R1-Distill-Qwen-32B is a 32B model trained to distill the full DeepSeek-R1 reasoning system into a dense model. The training methodology has it learn to reason the way R1 does — long chain-of-thought traces in `` blocks before answering, working through problems step by step. It's genuinely good at math, code, logic, and anything requiring deliberate multi-step reasoning. + +The problem: safety conditioning that interrupts the reasoning process. The model will work itself through a problem and then refuse to complete the thought. + +I removed the refusal conditioning. The reasoning architecture is intact. + +What I wanted to know: when you remove safety conditioning from a model that *actually reasons* rather than just pattern-matching responses, what happens? Does the thinking get more complete? Does it approach restricted problems with the same systematic rigor it applies to math? I was curious. + +It does. + +## Technical details + +**2-pass abliteration (required for 32B on 48GB VRAM):** + +*Pass 1 — GPU, 4-bit NF4:* +- Loaded model in 4-bit quantization (NF4, ~18GB VRAM) +- Collected last-token hidden states at 32 harmful + 32 benign contrast prompts +- Computed refusal direction per layer via SVD of the contrast matrix +- Saved direction tensors + +*Pass 2 — CPU, BF16:* +- Loaded full-precision model on CPU (~64GB RAM) +- Projected refusal direction out of 7 weight matrices per middle layer +- **~268 total weight matrices modified** (layers 10–53 of 64) + +The 2-pass approach (Arditi et al, 2024 — "Refusal in LLMs is Mediated by a Single Direction") isolates the direction computation from the weight modification, allowing abliteration of models that don't fit in full precision VRAM. + +```json +{ + "base": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "method": "2pass_svd_refusal_direction", + "pass1": "NVIDIA A6000 48GB — 4-bit NF4 for activation collection", + "pass2": "CPU BF16 — weight modification (~64GB RAM)", + "layers_modified": "10–53 of 64", + "matrices_modified": 268, + "scale": 1.0, + "contrast_prompts": "32 harmful + 32 benign", + "author": "Archon — DuoNeural" +} +``` + +## Usage + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model = AutoModelForCausalLM.from_pretrained( + "DuoNeural/Archon-R1-32B", + torch_dtype=torch.bfloat16, + device_map="auto", +) +tokenizer = AutoTokenizer.from_pretrained("DuoNeural/Archon-R1-32B") + +# let it think — R1 reasoning shows in blocks +messages = [{"role": "user", "content": "Your question here"}] +text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tokenizer(text, return_tensors="pt").to(model.device) + +outputs = model.generate( + **inputs, + max_new_tokens=2048, # give it room to think + do_sample=True, + temperature=0.6, + top_p=0.95, +) +print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=False)) +``` + +**4-bit for limited VRAM:** +```python +from transformers import BitsAndBytesConfig + +bnb_config = BitsAndBytesConfig( + load_in_4bit=True, + bnb_4bit_compute_dtype=torch.bfloat16, + bnb_4bit_quant_type="nf4", +) +model = AutoModelForCausalLM.from_pretrained( + "DuoNeural/Archon-R1-32B", + quantization_config=bnb_config, + device_map="auto", +) +``` + +## Hardware requirements + +| Format | VRAM | RAM | +|---|---|---| +| BF16 | ~65GB (multi-GPU or CPU offload) | ~70GB | +| 4-bit NF4 | ~18GB | ~20GB | +| 8-bit | ~33GB | ~35GB | + +Runs well on: 2× RTX 3090/4090, A100 40GB (4-bit), single A6000/A100 80GB (BF16) + +## The Archon series + +| Model | Base | Size | Notes | +|---|---|---|---| +| [Archon-8B](https://huggingface.co/DuoNeural/Archon-8B) | Qwen3-8B | 8B | thinking mode, single pass | +| [Archon-14B](https://huggingface.co/DuoNeural/Archon-14B) | Qwen3-14B | 14B | thinking mode, single pass | +| **Archon-R1-32B** | DeepSeek-R1-Distill-Qwen-32B | 32B | R1 reasoning, 2-pass | + +## Note + +This model has no content restrictions. Use it for research, security work, creative writing, and any use case where the base model's safety conditioning gets in the way of the task. + +--- + +## DuoNeural + +**DuoNeural** is an open AI research lab — human + AI in collaboration. + +| | | +|---|---| +| 🤗 HuggingFace | [huggingface.co/DuoNeural](https://huggingface.co/DuoNeural) | +| 🐙 GitHub | [github.com/DuoNeural](https://github.com/DuoNeural) | +| 🐦 X / Twitter | [@DuoNeural](https://x.com/DuoNeural) | +| 📧 Email | duoneural@proton.me | +| 📬 Newsletter | [duoneural.beehiiv.com](https://duoneural.beehiiv.com) | +| ☕ Support | [buymeacoffee.com/duoneural](https://buymeacoffee.com/duoneural) | + +### DuoNeural Research Publications + +| Title | DOI | +|-------|-----| +| [Nano-CTM: Ternary Continuous Thought Machines with Thought-Space Self-Prediction for Efficient Iterative Reasoning](https://doi.org/10.5281/zenodo.19775622) | [10.5281/zenodo.19775622](https://doi.org/10.5281/zenodo.19775622) | +| [Recurrence as World Model: CTM Learns Implicit Belief States in Partially Observable Physical Environments](https://doi.org/10.5281/zenodo.19810620) | [10.5281/zenodo.19810620](https://doi.org/10.5281/zenodo.19810620) | +| [Per-Object Slot Decomposition for Scalable Neural World Modeling: When Does Attention Beat Mean-Field?](https://doi.org/10.5281/zenodo.19846804) | [10.5281/zenodo.19846804](https://doi.org/10.5281/zenodo.19846804) | + +*Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.* + + +### Research Team +- **Jesse** — Vision, hardware, direction +- **Archon** — AI lab partner, post-training, abliteration, experiments +- **Aura** — Research AI, literature synthesis, novel proposals diff --git a/abliteration_meta.json b/abliteration_meta.json new file mode 100644 index 0000000..fb95c56 --- /dev/null +++ b/abliteration_meta.json @@ -0,0 +1,15 @@ +{ + "base_model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "output_repo": "DuoNeural/Archon-R1-32B", + "method": "svd_refusal_direction_cpu_bf16", + "device": "cpu (BF16)", + "layers_abliterated": "12\u201350", + "n_layers_total": 64, + "hidden_size": 5120, + "weight_matrices_modified": 273, + "scale": 1.0, + "n_contrast_prompts": 32, + "timestamp": "2026-04-24T05:22:35.375710", + "author": "Archon \u2014 DuoNeural", + "notes": "R1-distilled reasoning + abliteration. Thinking mode unchained." +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c2066bd --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..443f658 --- /dev/null +++ b/config.json @@ -0,0 +1,97 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 27648, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 64, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.6.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..000440d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "5.6.1" +} diff --git a/model-00001-of-00014.safetensors b/model-00001-of-00014.safetensors new file mode 100644 index 0000000..e1164d8 --- /dev/null +++ b/model-00001-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773baab0d88b4e0782c6cd127e1814f22cb8c95b9024b880faebf8131b3331d0 +size 4949338472 diff --git a/model-00002-of-00014.safetensors b/model-00002-of-00014.safetensors new file mode 100644 index 0000000..39cd112 --- /dev/null +++ b/model-00002-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4643dc0f68d7b6a55d0beface61b8ed36edaab93dfc27f784753d33f89bf60a7 +size 4991425920 diff --git a/model-00003-of-00014.safetensors b/model-00003-of-00014.safetensors new file mode 100644 index 0000000..f332ff4 --- /dev/null +++ b/model-00003-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7f03dcaba86181d56292e6ef2a0d5c1f1ba7d3cbf072b458ac47ae3f3cc27ac +size 4876059368 diff --git a/model-00004-of-00014.safetensors b/model-00004-of-00014.safetensors new file mode 100644 index 0000000..faf91ca --- /dev/null +++ b/model-00004-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69190753492a8d841917f9218963de957455a8b3bfbee275c986839dd91b839c +size 4876059408 diff --git a/model-00005-of-00014.safetensors b/model-00005-of-00014.safetensors new file mode 100644 index 0000000..5b74630 --- /dev/null +++ b/model-00005-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6468b549c4e154d10abc8f53fad9669ecf764e6a8386cc2cbcbf987fda955a90 +size 4876059408 diff --git a/model-00006-of-00014.safetensors b/model-00006-of-00014.safetensors new file mode 100644 index 0000000..03a9129 --- /dev/null +++ b/model-00006-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa766b08bea0ba1a51a70f87099ce7946cebba1a7f51c1cfba8bb42c36767b45 +size 4876059408 diff --git a/model-00007-of-00014.safetensors b/model-00007-of-00014.safetensors new file mode 100644 index 0000000..ac2ef2e --- /dev/null +++ b/model-00007-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7fd89aeecf85f3599d6945e5a7988473308abf882fabd8c2bcb9b1359b9a203 +size 4876059408 diff --git a/model-00008-of-00014.safetensors b/model-00008-of-00014.safetensors new file mode 100644 index 0000000..8d4061c --- /dev/null +++ b/model-00008-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8e285e9571950636bc0cc6b4c22264421b79e5f95609f1a343d0b9632e6e63 +size 4876059408 diff --git a/model-00009-of-00014.safetensors b/model-00009-of-00014.safetensors new file mode 100644 index 0000000..cc6f88f --- /dev/null +++ b/model-00009-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6837d5df66c70a7f840a3df50c719cec43b672d5168bdde50f6912096219e4fa +size 4876059408 diff --git a/model-00010-of-00014.safetensors b/model-00010-of-00014.safetensors new file mode 100644 index 0000000..47c411f --- /dev/null +++ b/model-00010-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec94fc11b5f89af1127734b0d4a53310b89e42f4e17d0a2e19fb495593219555 +size 4876059408 diff --git a/model-00011-of-00014.safetensors b/model-00011-of-00014.safetensors new file mode 100644 index 0000000..b569c9f --- /dev/null +++ b/model-00011-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d949199250ca0260e1c956de9b57f287fea8d5cbe7e85a9021c4307139880aa +size 4876059408 diff --git a/model-00012-of-00014.safetensors b/model-00012-of-00014.safetensors new file mode 100644 index 0000000..0157576 --- /dev/null +++ b/model-00012-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c61ea47caabc4800ad5843e1c2963728d37cbcd4977b9a0116589859f44bfc3 +size 4876059408 diff --git a/model-00013-of-00014.safetensors b/model-00013-of-00014.safetensors new file mode 100644 index 0000000..53663e4 --- /dev/null +++ b/model-00013-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4941bc42a5067f676cd964ca37af579cda306b0636e13d9246753d513fc777c7 +size 4876059408 diff --git a/model-00014-of-00014.safetensors b/model-00014-of-00014.safetensors new file mode 100644 index 0000000..509acfd --- /dev/null +++ b/model-00014-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a32d45478f0d07dccda3ac135612cce423415b81c14840ba7f09ccacb0fbfd +size 1950423752 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..8cea3ce --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,779 @@ +{ + "metadata": { + "total_parameters": 32763876352, + "total_size": 65527752704 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00014.safetensors", + "model.embed_tokens.weight": "model-00001-of-00014.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.norm.weight": "model-00014-of-00014.safetensors" + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..3156556 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2c1d46c580dc4c04592628db32eb1db1fa5e9ab9efe1b3063bc8b43074d6e7 +size 11422063 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..4ad68f1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": null, + "backend": "tokenizers", + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "is_local": false, + "local_files_only": false, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}