commit b8149bf53fddb01ae7de56536c3785c5d7b7f181 Author: ModelHub XC Date: Sat Jul 11 16:57:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantTrio/DeepSeek-R1-0528-Qwen3-8B-GPTQ-Int4-Int8Mix Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..d42fae9 --- /dev/null +++ b/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2023 DeepSeek + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..29eea10 --- /dev/null +++ b/README.md @@ -0,0 +1,184 @@ +--- +library_name: transformers +license: mit +pipeline_tag: text-generation +tags: +- DeepSeek-R1-0528 +- GPTQ +- Int4-Int8Mix +- 量化修复 +- vLLM +base_model: + - deepseek-ai/DeepSeek-R1-0528-Qwen3-8B +base_model_relation: quantized +--- +# DeepSeek-R1-0528-Qwen3-8B-GPTQ-Int4-Int8Mix +基础型 [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://www.modelscope.cn/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B) + +### 【模型更新日期】 +``` +2025-05-29 +1. 首次commit +``` + +### 【依赖】 + +``` +vllm==0.9.0 +transformers==4.52.3 +``` + +
+### 【💡新版 VLLM 注意事项💡】 + +#### 1. 建议使用V0推理模式 +启动vllm之前，先设置环境变量 +``` +export VLLM_USE_V1=0 +``` +
+ + +### 【模型列表】 + +| 文件大小 | 最近更新时间 | +|---------|--------------| +| `6.9GB` | `2025-05-29` | + + + +### 【模型下载】 + +```python +from modelscope import snapshot_download +snapshot_download('tclf90/DeepSeek-R1-0528-Qwen3-8B-GPTQ-Int4-Int8Mix', cache_dir="本地路径") +``` + + +### 【介绍】 +## DeepSeek-R1-0528 + + + + +
+ DeepSeek-V3 +
+
+
+ + Homepage + + + Chat + + + Hugging Face + +
+ +
+ + Discord + + + Wechat + + + Twitter Follow + +
+ +
+ + License + +
+ + +

+ Paper Link👁️ +

+ + +## 1. Introduction + +The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro. + +

+ +

+ +Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question. + +Beyond its improved reasoning capabilities, this version also offers a reduced hallucination rate, enhanced support for function calling, and better experience for vibe coding. + +## 2. Evaluation Results + +### DeepSeek-R1-0528 + For all our models, the maximum generation length is set to 64K tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 16 responses per query to estimate pass@1. +
+ +| Category | Benchmark (Metric) | DeepSeek R1 | DeepSeek R1 0528 +|----------|----------------------------------|-----------------|---| +| General | +| | MMLU-Redux (EM) | 92.9 | 93.4 +| | MMLU-Pro (EM) | 84.0 | 85.0 +| | GPQA-Diamond (Pass@1) | 71.5 | 81.0 +| | SimpleQA (Correct) | 30.1 | 27.8 +| | FRAMES (Acc.) | 82.5 | 83.0 +| | Humanity's Last Exam (Pass@1) | 8.5 | 17.7 +| Code | +| | LiveCodeBench (2408-2505) (Pass@1) | 63.5 | 73.3 +| | Codeforces-Div1 (Rating) | 1530 | 1930 +| | SWE Verified (Resolved) | 49.2 | 57.6 +| | Aider-Polyglot (Acc.) | 53.3 | 71.6 +| Math | +| | AIME 2024 (Pass@1) | 79.8 | 91.4 +| | AIME 2025 (Pass@1) | 70.0 | 87.5 +| | HMMT 2025 (Pass@1) | 41.7 | 79.4 | +| | CNMO 2024 (Pass@1) | 78.8 | 86.9 +| Tools | +| | BFCL_v3_MultiTurn (Acc) | - | 37.0 | +| | Tau-Bench (Pass@1) | - | 53.5(Airline)/63.9(Retail) + +
+Note: We use Agentless framework to evaluate model performance on SWE-Verified. We only evaluate text-only prompts in HLE testsets. GPT-4.1 is employed to act user role in Tau-bench evaluation. + +### DeepSeek-R1-0528-Qwen3-8B +Meanwhile, we distilled the chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3 8B Base, obtaining DeepSeek-R1-0528-Qwen3-8B. This model achieves state-of-the-art (SOTA) performance among open-source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3-235B-thinking. We believe that the chain-of-thought from DeepSeek-R1-0528 will hold significant importance for both academic research on reasoning models and industrial development focused on small-scale models. + +| | AIME 24 | AIME 25 | HMMT Feb 25 | GPQA Diamond | LiveCodeBench (2408-2505) | +|--------------------------------|---------|---------|-------------|--------------|---------------------------| +| Qwen3-235B-A22B | 85.7 | 81.5 | 62.5 | 71.1 | 66.5 | +| Qwen3-32B | 81.4 | 72.9 | - | 68.4 | - | +| Qwen3-8B | 76.0 | 67.3 | - | 62.0 | - | +| Phi-4-Reasoning-Plus-14B | 81.3 | 78.0 | 53.6 | 69.3 | - | +| Gemini-2.5-Flash-Thinking-0520 | 82.3 | 72.0 | 64.2 | 82.8 | 62.3 | +| o3-mini (medium) | 79.6 | 76.7 | 53.3 | 76.8 | 65.9 | +| DeepSeek-R1-0528-Qwen3-8B | 86.0 | 76.3 | 61.5 | 61.1 | 60.5 | + +## 5. License +This code repository is licensed under [MIT License](LICENSE). The use of DeepSeek-R1 models is also subject to [MIT License](LICENSE). DeepSeek-R1 series (including Base and Chat) supports commercial use and distillation. + +## 6. Citation +``` +@misc{deepseekai2025deepseekr1incentivizingreasoningcapability, + title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, + author={DeepSeek-AI}, + year={2025}, + eprint={2501.12948}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2501.12948}, +} +``` + +## 7. Contact +If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com). diff --git a/config.json b/config.json new file mode 100644 index 0000000..44043c5 --- /dev/null +++ b/config.json @@ -0,0 +1,51 @@ +{ + "name_or_path": "tclf90/DeepSeek-R1-0528-Qwen3-8B-GPTQ-Int4-Int8Mix", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 131072, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "rope_type": "yarn", + "factor": 4.0, + "original_max_position_embeddings": 32768, + "attn_factor": 0.8782488562869419 + }, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.51.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936, + "quantization_config": { + "quant_method": "gptq", + "bits": 4, + "group_size": 128, + "sym": false, + "desc_act": false, + "dynamic": { + "+:model.layers.*.self_attn.o_proj.*": { + "bits": 8 + }, + "+:model.layers.*.mlp.down_proj.*": { + "bits": 8 + } + } + } +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..f9291c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/figures/benchmark.png b/figures/benchmark.png new file mode 100644 index 0000000..7af4bd3 Binary files /dev/null and b/figures/benchmark.png differ diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..79ddb8b --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b7feb2c43bf7406677514c285a10266bfdceca183f10a88c63c6c759cc5b31 +size 3803607656 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..5fbe93d --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551cceeeb1ed3b8de6d5561700384fb13359a30ef7b7360286327a40aef27e02 +size 3517706272 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b2ee0fa --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1162 @@ +{ + "metadata": { + "total_size": 7321184256 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "model-00002-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.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.g_idx": "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.mlp.gate_proj.g_idx": "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.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.g_idx": "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.o_proj.g_idx": "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.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.g_idx": "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.v_proj.g_idx": "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.norm.weight": "model-00002-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5e6be21 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d3a3ffb1ff38eb6a22f8a2d207306bfa3ea2499ff70df4baeaa559bf7453c7 +size 7032822 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c24fd8e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": true, + "model_max_length": 131072, + "pad_token": { + "__type": "AddedToken", + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "sp_model_kwargs": {}, + "unk_token": null, + "tokenizer_class": "LlamaTokenizerFast", + "chat_template": "{% 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='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- 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｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}" +} \ No newline at end of file