From 5f5033509713b66199468e9aa972e9997cbab1c0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 3 Aug 2026 02:29:13 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: agentica-org/DeepCoder-14B-Preview Source: Original Platform --- .gitattributes | 49 +++ README.md | 131 ++++++ config.json | 30 ++ configuration.json | 1 + generation_config.json | 10 + model-00001-of-00012.safetensors | 3 + model-00002-of-00012.safetensors | 3 + model-00003-of-00012.safetensors | 3 + model-00004-of-00012.safetensors | 3 + model-00005-of-00012.safetensors | 3 + model-00006-of-00012.safetensors | 3 + model-00007-of-00012.safetensors | 3 + model-00008-of-00012.safetensors | 3 + model-00009-of-00012.safetensors | 3 + model-00010-of-00012.safetensors | 3 + model-00011-of-00012.safetensors | 3 + model-00012-of-00012.safetensors | 3 + model.safetensors.index.json | 586 +++++++++++++++++++++++++++ special_tokens_map.json | 23 ++ together-ai-branding-lightOnDark.png | Bin 0 -> 28987 bytes tokenizer.json | 3 + tokenizer_config.json | 195 +++++++++ 22 files changed, 1064 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00012.safetensors create mode 100644 model-00002-of-00012.safetensors create mode 100644 model-00003-of-00012.safetensors create mode 100644 model-00004-of-00012.safetensors create mode 100644 model-00005-of-00012.safetensors create mode 100644 model-00006-of-00012.safetensors create mode 100644 model-00007-of-00012.safetensors create mode 100644 model-00008-of-00012.safetensors create mode 100644 model-00009-of-00012.safetensors create mode 100644 model-00010-of-00012.safetensors create mode 100644 model-00011-of-00012.safetensors create mode 100644 model-00012-of-00012.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 together-ai-branding-lightOnDark.png create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json 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/README.md b/README.md new file mode 100644 index 0000000..7c9ab01 --- /dev/null +++ b/README.md @@ -0,0 +1,131 @@ +--- +license: mit +library_name: transformers +datasets: +- PrimeIntellect/verifiable-coding-problems +- likaixin/TACO-verified +- livecodebench/code_generation_lite +language: +- en +base_model: +- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B +pipeline_tag: text-generation +--- + +
+DeepCoder-14B-Preview +
+šŸš€ Democratizing Reinforcement Learning for LLMs (RLLM) šŸŒŸ +
+
+
+
+ + Code + + + Blog + + + X.ai + + + Hugging Face + + + Together AI + +
+ + + +## DeepCoder Overview +DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths. The model achieves 60.6% Pass@1 accuracy on LiveCodeBench v5 (8/1/24-2/1/25), representing a 8% improvement over the base model (53%) and achieving similar performance to OpenAI's o3-mini with just 14B parameters. + +
+ +
+ +## Data +Our training dataset consists of approximately 24K unique problem-tests pairs compiled from: +- Taco-Verified +- PrimeIntellect SYNTHETIC-1 +- LiveCodeBench v5 (5/1/23-7/31/24) + +## Training Recipe + +Our training recipe relies on an improved version of GRPO (GRPO+) and iterative context lengthening, introduced in DeepScaleR. + +### GRPO+ + +We enhance the original GRPO algorithm with insights from DAPO to enable more stable training: + +- **Offline Difficulty Filtering:** DAPO employs online dynamic sampling, discarding both entirely correct and entirely incorrect samples on the fly. While this helps maintain a more stable effective batch size, it introduces significant runtime overhead due to rejection sampling. Instead, we perform offline difficulty filtering on a subset of coding problems to ensure the training dataset remains within a suitable difficulty range. +- **No Entropy Loss:** We observed that including an entropy loss term often led to instability, with entropy growing exponentially and ultimately collapsing training. To mitigate this, we eliminate the entropy loss entirely. +- **No KL Loss:** Eliminating KL loss prevents the LLM from staying within trust region of the original SFT model. This removal also obviates the need to compute log probabilities for the reference policy, thereby accelerating training. +- **Overlong Filtering** **(from DAPO):** To preserve long-context reasoning, we mask the loss for truncated sequences. This technique enables DeepCoder to generalize to 64K-context inference despite being trained with a 32K context. +- **Clip High (from DAPO):** By increasing the upper bound in GRPO/PPOā€™s surrogate loss, we encourage more exploration and more stable entropy. + +### Iterative Context Lengthening + +Our original `Deepscaler-1.5B-Preview` scaled long context training from 8Kā†’16Kā†’24K, achieving 33ā†’38ā†’43% on AIME respectively. Similarly, `Deepcoder-14B-Preview` is trained on 16Kā†’32K, achieving 54ā†’58% on LiveCodeBench (v5). `DeepCoder-14B-Preview` successfully generalizes to longer contexts when evaluated at 64K context, reaching 60.6%. + +DeepCoder generalizes better to long contexts than the base distilled model, due to DAPO's overlong filtering. However, it's longer responses are often truncated when the max length is capped at 16K, which can lower its scores. + +| **Model** | **16K** | **32K** | **64K** | +| --- | --- | --- | --- | +| **DeepCoder-14B-Preview** | 45.6 | 57.9 | 60.6 | +| **DeepSeek-R1-Distill-Qwen-14B** | 50.2 | 53.0 | 53.0 | + +A more detailed description of the training recipe can be found in our [blog post](https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51). + +## Evaluation + +We evaluate `Deepcoder-14B-Preview` on various coding benchmarks, including LiveCodeBench (LCBv5), Codeforces, and HumanEval+. + +| **Model** | LCB (v5)(8/1/24-2/1/25) | Codeforces Rating | Codeforces Percentile | HumanEval+ | +| --- | --- | --- | --- | --- | +| **DeepCoder-14B-Preview (ours)** | ***60.6*** | ***1936*** | ***95.3*** | ***92.6*** | +| **DeepSeek-R1-Distill-Qwen-14B** | 53.0 | 1791 | 92.7 | 92.0 | +| **O1-2024-12-17 (Low)** | 59.5 | **1991** | **96.1** | 90.8 | +| **O3-Mini-2025-1-31 (Low)** | **60.9** | 1918 | 94.9 | 92.6 | +| **O1-Preview** | 42.7 | 1658 | 88.5 | 89 | +| **Deepseek-R1** | 62.8 | 1948 | 95.4 | 92.6 | +| **Llama-4-Behemoth** | 49.4 | - | - | - | + +## Serving DeepCoder +Our model can be served using popular high-performance inference systems: +- vLLM +- Hugging Face Text Generation Inference (TGI) +- SGLang +- TensorRT-LLM + +All these systems support the OpenAI Chat Completions API format. + +### Usage Recommendations +Our usage recommendations are similar to those of R1 and R1 Distill series: +1. Avoid adding a system prompt; all instructions should be contained within the user prompt. +2. `temperature = 0.6` +3. `top_p = 0.95` +4. This model performs best with `max_tokens` set to at least `64000` + +## License +This project is released under the MIT License, reflecting our commitment to open and accessible AI development. +We believe in democratizing AI technology by making our work freely available for anyone to use, modify, and build upon. +This permissive license ensures that researchers, developers, and enthusiasts worldwide can leverage and extend our work without restrictions, fostering innovation and collaboration in the AI community. + +## Acknowledgement +- Our training experiments are powered by our heavily modified fork of [Verl](https://github.com/agentica-project/verl), an open-source post-training library. +- Our model is trained on top of [`DeepSeek-R1-Distill-Qwen-14B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B). +- Our work is done as part of [Berkeley Sky Computing Lab](https://skycomputing.berkeley.edu/) and [Berkeley AI Research](https://bair.berkeley.edu/). + +## Citation +```bibtex +@misc{deepcoder2025, + title={DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level}, + author={Michael Luo and Sijun Tan and Roy Huang and Ameen Patel and Alpay Ariyak and Qingyang Wu and Xiaoxiang Shi and Rachel Xin and Colin Cai and Maurice Weber and Ce Zhang and Li Erran Li and Raluca Ada Popa and Ion Stoica}, + howpublished={\url{https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51}}, + note={Notion Blog}, + year={2025} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3d38ed6 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "agentica-org/DeepCoder-14B-Preview", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 131072, + "max_window_layers": 48, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.47.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3573d8f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "max_tokens":64000, + "transformers_version": "4.47.1" +} diff --git a/model-00001-of-00012.safetensors b/model-00001-of-00012.safetensors new file mode 100644 index 0000000..2301100 --- /dev/null +++ b/model-00001-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f12717798c9a0434626fc08bc29eb48b545a414838f0cd2279a1b8a67a5c1a +size 4750149992 diff --git a/model-00002-of-00012.safetensors b/model-00002-of-00012.safetensors new file mode 100644 index 0000000..bfe9c9f --- /dev/null +++ b/model-00002-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a91cbb872bf40ff4dd6a762deba4fee7ff30d96a059ba1811323ecac6b62366 +size 4970575640 diff --git a/model-00003-of-00012.safetensors b/model-00003-of-00012.safetensors new file mode 100644 index 0000000..95191e9 --- /dev/null +++ b/model-00003-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8bc8e03a8579dd48ed4066b7f786f2644e71650c551f03f0a37e8912434dc8f +size 4939106528 diff --git a/model-00004-of-00012.safetensors b/model-00004-of-00012.safetensors new file mode 100644 index 0000000..ccd7532 --- /dev/null +++ b/model-00004-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a36ae65eacab1797cbdef6cc399a58ca4b31b487cd5ed6e749eebfad64d2e21 +size 4970575688 diff --git a/model-00005-of-00012.safetensors b/model-00005-of-00012.safetensors new file mode 100644 index 0000000..0083d3e --- /dev/null +++ b/model-00005-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d3a565bcafe82d98ab6e46ce7e9bc3501b8c27b53be1d2e619de928b75dafd +size 4939106568 diff --git a/model-00006-of-00012.safetensors b/model-00006-of-00012.safetensors new file mode 100644 index 0000000..c0a0040 --- /dev/null +++ b/model-00006-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b180c5ec09011ea4fb1cff9a5dbbd5fb125931757333ff8abaa0cc230993140 +size 4970575688 diff --git a/model-00007-of-00012.safetensors b/model-00007-of-00012.safetensors new file mode 100644 index 0000000..e49e90b --- /dev/null +++ b/model-00007-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba331d3a66b4b5215ecdca8ab28f3133cc3160d0f51a131430bc8b6f7626c4d +size 4939106568 diff --git a/model-00008-of-00012.safetensors b/model-00008-of-00012.safetensors new file mode 100644 index 0000000..e37dd73 --- /dev/null +++ b/model-00008-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac0cebeecf4b4d425040cae6ad1d6c6f7a6ac21ad1087e8ca91698c5da72f15 +size 4970575688 diff --git a/model-00009-of-00012.safetensors b/model-00009-of-00012.safetensors new file mode 100644 index 0000000..4c8982a --- /dev/null +++ b/model-00009-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52214dc482f83ebd0c615096f66d210624e5b9b52f132dc8e1667d535521737 +size 4939106568 diff --git a/model-00010-of-00012.safetensors b/model-00010-of-00012.safetensors new file mode 100644 index 0000000..c4a7fe8 --- /dev/null +++ b/model-00010-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac1245d69e7cd6a232b0fa7e2a351059ada256d55046249c66d9346508a8914 +size 4970575688 diff --git a/model-00011-of-00012.safetensors b/model-00011-of-00012.safetensors new file mode 100644 index 0000000..71db845 --- /dev/null +++ b/model-00011-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6498f7264edc3798381a1343bb0e22a6b966e5407af30e3bd4b4813fcfd4e537 +size 4939106568 diff --git a/model-00012-of-00012.safetensors b/model-00012-of-00012.safetensors new file mode 100644 index 0000000..f9e4f0a --- /dev/null +++ b/model-00012-of-00012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c52da3bda5075f93854fd4d7683623a101cd36a10d53cc2b83dde6ca96b6af55 +size 4781639680 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..48dcb3d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,586 @@ +{ + "metadata": { + "total_size": 59080134656 + }, + "weight_map": { + "lm_head.weight": "model-00012-of-00012.safetensors", + "model.embed_tokens.weight": "model-00001-of-00012.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00012.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", + "model.layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.16.input_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.19.input_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.20.input_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00012.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", + "model.layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.28.input_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", + "model.layers.29.input_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00008-of-00012.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", + "model.layers.33.input_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.34.input_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", + "model.layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00010-of-00012.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", + "model.layers.42.input_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.46.input_layernorm.weight": "model-00012-of-00012.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", + "model.layers.47.input_layernorm.weight": "model-00012-of-00012.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00012-of-00012.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00012-of-00012.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00012-of-00012.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00012.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", + "model.norm.weight": "model-00012-of-00012.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<ļ½œbeginā–ofā–sentenceļ½œ>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<ļ½œendā–ofā–sentenceļ½œ>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<ļ½œendā–ofā–sentenceļ½œ>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/together-ai-branding-lightOnDark.png b/together-ai-branding-lightOnDark.png new file mode 100644 index 0000000000000000000000000000000000000000..98b27584a8151eb401e5ea75f3d591c1fcecc824 GIT binary patch literal 28987 zcmeFYby(Ef7dQGv4xy9?2uLX?B~prXD5Z#WODQEFB``D$qIBp11SACsiJ{9Oh87Tp zP={s&>7iqgyn8&q<9YA@_x|_tJRau^?zPwYtlVp_9igS6N_FniIS7KN?%z|=fgo}h z2qM}gCk5Z!jlNR_{yOV=&)6M;7-%w7b%x;3QE@UjKtHcS<Nd_dBFey-~LU&8+vir)zQe{2;ef3y7$ zSg61rX{^aLqpXxxYhjiezRyIP+U>EoS=Ajnr`deG_Xzf{>1Ktm+BSxV`yB4#h)#!T zXgB3Jr!?~_zm>aFrTnq)=m}V*TwHi9ZFzWjCD##GP)xX2{L(X@mqFjL{}^^o`DAg@ zC^P5GbJ27&+c3Zeym8ewfEGE^DWb*_78ny=3!AB%w5a&)J!u2IIEc3V3pIgVTH5ix z17#&smG*6(BPVm^c7LRCb9M3$+o1m6zbE{gwC}LWKsF=^siyJ7h;&qVW^L;3+}XfV z^FO`>ryX_v9u>ZCDAOmxSL>65a+CezlS~l?6Z?`PFV1v{{qac4ziLuVO-n0@ClonE z<@o;F6Cp>>WnRs8SLMMU8lfxtFu314JF?IJg(u>w$zls@J8!t0jjYsvtMj&T5REXJ z`t|+)R@;9?8t+8>QSoc1ugY|PR$Lx8hQZZ?x~WkdfW0UjC2jdTb-Sd|D?k^qz_f%o zPm2xL9}!gJuk4eP$5BbF)E*XI_k|h+N>^)uYf4(n;qSm|;r5IW@CiS!S9Jl^{{&S} z1#AuE7pvy~iLY%tBGM@0;tFEx|1|q}S=T2=(>PA!5A&o?Mbn))XWU`2ekQj6r~GZZ za?&VS(}#ICrT^6?6!JA}OXdHKWiSIqMHbTtj@WN6%ZQ z_uP4%C;rPvDz*R=K$(;CgdNEyk};%7yLs1b*7iSYI`K<5Go`eyVO;Cx70wf>l>Vuj zNx8b<|JXFLV~jnG3=e8w3y*j4WI%F$w%{2a^%qUQ!I9~@|9`}n&*CZl2DEOpw2Z%< z_X`L$IM}?mPunR@SLqq&6K2{6HZd+ae|Yw{5ls(>4v!m^>})OP`^Oxh|C=EH=;r@N zCUO=eSBW8nd!IY7 z?jx2H?cR`P@z^u6*$qTHL$Jz>uB1E7$EEg4GC{4=?x#ZXU5Jr#jxQsp-xSYJyuS&T zh%0@dFO<26A3yCq_C%iUioilnd-L}L9;<5vnAQGX(y=DjAho~i1}yw!zxgjLA8SMA z>NK|E{N=++O{&D=TX-DEehMTz~<+vmL`g4%;0JF5@(TeUD z`y=nZ_2$#0Fn1Q(wOOs6%)rCdS{xMz_95 z4$>lVo4@8_!t7riV9JqsMC^sSL&;r9&pQV?H7q@-doEek=Vew~lyY)Xcd8}9=Has-zi2pT z5eL)k9-@9g+@Z{GZkHp&C&gsmuHXe=LOi9MGYhM>$BsKIzN?d$8T03wj{H(`q~C0q z*I!^t-AlvYhT&gcK`_be$Z(!8Zyw@L55v9fHd1t-#(z4rD>LkN6ZPn2mG|n=TQ>`t zuw+Lr>{N_tpDmqz@YpJP-9T6(-EU8(b34sHY0YS*LsM>SL-JNdbvymIZ>S}LkYAgy4 zat1h+Bbz|$>bVYy@V`g zH^j4a6J5^YUw3OCqP&CTX>e*zSZUsq;S7uwQl6xkK9*6jduC0Gs6AY~C@J9lxb#c* zOPF;lr+`*Si(3Fk$B%%cq5ixLVM3utiH2306C6nCNE2ru#OLgvdi-H92n3t1y#`&9Gu(ZsabT;%L&M>Hi(rAMo zP;a36$ztT6W~W`+{-fjR2Wo_42u;^ESZs!qBCGp$5^#f4u5&E|)z%O_>D7FJ%*%m7 z$bfdURQUFD0lUrIdwxq&thouV9+Od+o}?raOUPmH_hq9dGdBaB+l;PF-1Q;$P6+wd zARii*mJgG#bjwH!%W#ZG_U;b}EJ*MtO5iGlMG-6UOXdrt9Po;<%Fq0`DmO|s)`@~j z2mFHY?X85Vmn*IbfYWYRA})dbhHG%}(igkBCQTRl+Q+OU&hHzD{NqEySc`nzakU%z zGuRetZm$wjKdHm+$%J5Kp*yoPpEN4vbvm%bT0H=%!8Ho`FnqPuc#_1FA7f7CaHu{q zKUZB$j>o5e%K5v??1Lp*rf|pko1eG!Be*0f5DbI&ou0!X0t=^8bi%0yvfK?6-Z zGQWnyNM_g5w<7WW&m~HQI)wWw8He1(5jQfX`rG6OnXVSz4y8}PV9=^cvVh++n;-sLkPT zIp2%O?jN~lb2gVv+xjI-?N9HDf;`*S-h!$V#}5^aB=QSYgg|Xyxf7k6db4SUiWi2{Ox-%mN^h5#bFkopLnuqnP__;BtN!ZEfoDL(c{5QmqJ z2)dT3GsV1gtgCHuk)C7qQy7HiAP;V;;)1p2$26ecvcj?oj*?5b(i(mX zHy9Hx{O0+%W6JTuqquTub26szz1ZXRGR36<9K~Q1?y{>|4-0C2OtC+x6+5k!B78|= zAq_v(D{%tP&U}?|(_Yv}UTTceJ9=-zjt3rC=1^uQrAlj@C@%nOXAX4{Y^z@Xq3^93 z+OkMrA@GEyCUZRYzVJCf^5lvgGyC(-C(RUHKCtt#ZITNiTLPSKor=0t%Udg_)h|W2 zHkIv4Ns|uo651x%)_d6^uNb?eG`VPkepl$hNSBcgK?g#q#c zif&fqfd*qmbCx`cowEY4t^$FIkd4bU{1a7Z{6c=j8Ea5ct+#s0+M*SMLxOdu;Izw> z>Jr?q!YAKa#cD657<}5y7WI$gb2U=_elwkjJh#Wqml;V!juG5Q)NpHiJJ7b7b0L6g zRo0ssCc|gNi9*FW@);Mm;1;BmGpwvWG=jbTzbwl9j5^Bq*qz}J)3CMjdKNTXi{pJhiee<9&>K96+V z-X%UcG&hZ0c{aTIX@0<1W^LrEC6i#A>=R0Q360`P&gp&fusvj!Pg3D(Cp!No>veHO8jHoU!;m|A%4E>$n_wmzvifzB#7x`UNBgafRyXQ>%7r%BJt`G z*#)Xw-}7E~5c9dBK3AD-Q0m0RtsnB(`oAR8!WOLNp>3FH(HhCb-h>Ej=FL5SV*akz zk{9rWqEvVN>l|yunAp*}a7!vULt`2vr`(>mjqhbS@f+Uv zW$5>z^cw#PDEdmK^b3~$LN|P%zqz%Y1j<4y9O6gZ>h$>OaX{a=1roF0YxQy^h0v1f zBJ|kSPWcCTxSBOLs_kgqm}yJn-6>l?cd71KT{&DptW}N#q;)0T-`egkecxm;X>EZ` z2JN;mndU8zz*FW4=kE*Uhy8z%W^Jp>z-Us?608(#hiRS0N~WJ&hV6i{3v;n2@3SKB zgddkaRPvYkPW4GFkP8;Cy0D5F;f?_&Wcl;@wtRciiWf6&s?|fSnxtmN&AEg0E@4vk z>FP6G%h>5!(c;&8+qKarrwx-``nZ$kz=_k{d-$0-&r@5LV%az$%uW>3$>ol~Ernp> z&^ggix6Bd7Jx+ws@+wc<0_MmCNsJbHl7?>cD+QIrc(;cw&s$Zd(f!Z)`&*QIKb6sY zQ^3v~J=xouZ8N)^?LH_!r+x=~E&DjlqO&Y$&+=KPp6v;}h1y#VD{<;iGV?A2YnVxq zK}L}yKUn)(QvfZkOT0TuTzd*m#5{^>4;!IU7nlvd7L)41p7wS!s5wz;FN9&6=_DlX zOc&iHW4Bp%{{SlaCG3;KSR?k6L#LTqKPtS_5GdnA^tVHTru$i{1#*JqAJJ?&;!fn7 zn)B}Md>C7=jqKl@>=E5wT=xt}I(~Z~RLmLt7(^`>t{Ht;EZOqgT{)HZyMbyzYVUUk3b6~CZ%fw@r__MH&go6 z|N18Egh!X(D1Om01`b{#6OO*8I8ggZEN;;^+b>9N6-~Q9v+wbn$Do!9DwKDW$SY40 zFKmJg>+X0O_EL6ak=1tH5*A76?|GK~-T9>VY0%!PyHUF`2o6ge2e;GuU@k+bV=Ut7xc?{Jt0r(|71V^5X46 zfPaA5IuGr^bF=9=V_cJF5o5JM`Sl3{-N##A;p>lza8SV4DUOqr^jUVq%u2+}H@?7O z7VdELY_G!h%ID^c%psevrwF0^<7fdZZ+VtOw>Q0!xf%VtzRa87_CK#Mb@tz-MMh-B ziL;t@+uvy2)DdP{&DgYp#d3{L*Y+}yBbaH@JJ+PEH30~2%oefmkg0vbmCW1pVB+z< zPpx5Fk44k_DivMjiOoxb7?3Q_x`QK-RYW<;hhhoAk%(sIGKmaeS|Xv6Er(ZN7`OVf zQ^=i-j=APNIzHu$YbPeFb30$h)XL=4KTl#7MiLo>4q>wEo{_9kOr2h9La;X9I?(@) zK5A{imnbQ(#h-$924hDi(F0BTbt;b+bt@c^+jxv50y&=d+6|M%c;dbQ-l-{!zET5IkNd7J=mD%-F=d|W`}6f7{;p(wXm@v!^Fa1KUJ{0} z5u)ge6Dh-|MaEW3kE^O44KS|OB}AgzX+-LNMTbv!DGFsz&pkj7)$)qUWjDAf_~c}9 z65l7K^LwH|Oh=2n(;9VU`rbG(dVGY6cW*a1zqbv|Md)xV9i^qu-jnNEyVL{_Oc=9+ z(Tb6=oL)pa(Ojp@i>YZCY+8|5Ic;7b3$lo1YH$3-&pF?dfH$;uZ9O!|=3Jj>Rw=>P zp*M5=#}B(d6ZzM29C(VROR{6BiAQ&zS&T8YS9_-#oT&>x^4qGtG}mbAGn?ukJLz{& zaeRDITJ*lzvBhlc=J=`gg7?d*w;3GSi9*vVtIAHb<&H~Kk=W>byUHYko^*?#9OY ztfEo_+au;IcbB!<%5V823=*WW-R=T^RASbVl{rhgHzhV^S9HjPdb#x!knuI2**^rW z;Uu=11X9zs3f~R{dHfLVRr8+<5$JM?6~GqgBfo|Pr2Tr zf;Tn^bd-ejy|aDo_7ks%LY@2dp4Ex+>)GEU_Ye2GzkkN-{=s|{$jB-ldB3awEjl1@ z{XizAzrRvZ?-tyv$l{4O(XHjPQ@8tf1sxJ+*RAxry7^s9SKO5v;==J(K}j#d7MJi5 zZt?p8cV>{EgGvL*w;3`27!4LZN(2vcB-Tvo7Ga-N#J!7+5@8hQ*sQHsA)gUrPF4#gHrW8J^@G$DPC#mt(l zAg}S!u2XGs_~c&$6m$wfUo##YR-xv6>TY-abjNkB^*`ElxP?TZM5^yPSinri>*v}A1WqDA=@2Vx278EG6~^fBNfvg82~^(s%~Ls4ZVY1`$} z!R7@qq>G0~Y}-;i`tg}XjdT*h0KUO7BBy;h)%NMJ!o%M3x0io}3sw+M3~Oe*cfp)I zn;(q(MTvA7pa5KPfn42%W2LE@cABkbOg*%}zHg!0ej0H?#VzMT!sQH0VZ*ZcOIiOM z{C5^0GW=I^&G*3KJ-c1bgJGEk+A%l20FzDoA#CuNWqZ_!Q;g{(OFWqZC~snIzyVa} z;rJ$2<^bOS`mtHBdlwCT_L4@}WbMx^X80Op?>5P(8xHb0S%(E*S?orz97@L2j@~)Q zx|ul`Ho1Cnln5&bxD+B-!lEvYlpEK%K{b{+?z3Z8G|mX1w5T(l;wCzA4Bt#DevHezl2D zc0q4sy!@vx)Ef{fQ(STN?!sWRQ+>TMi-&hS*yO|(iJo0bTQd3e?zRs!yX&=XMT4n4 z)3yDEy{H*Hs~WE&?et)}r(_Fp92H5_$+gmLEkrXMc33I;oo=Z` zEa2j?aUvxvdYXIKm}5=z+HNrlobFz~Pc$&MS*RnUQ_%cCMt8SV#T>C*naMqzvT`xw z-neAZ@);)lDwiXErBL;Lvx9t`*56yC^qBsN)iz0l;SYg29*pEl^|I37dvHZO>RXdr zI@3wFvQ)opn!}S@eB3xHcC0jp>X%ubN}5iVfouOtt(cnKEkJGBehBFg;N_95S&Z1l zG9iK2$|R?s`>}KbI1U!v_Q^!R5_U>QC7rR0^gTLL@YXQ}bq-Q)b?Wp1YpF-ds}b3V zr2f}YUW1u80vZd_?!|GF)TwBy8L##6427KOQieg;tMuZr1+qo@Y){urtjQ#DYwB`+ zefAi;E~cy4F;+#A#3rpSBnGh6GER9*1gGLn?9@sw7qTdFx%yGxjF&8=2>{Et$8&s#(R>DOyw8U3uwg)!F^$@prXPCm(+~0j(Dv0uosF z{aCq=pn#`E%H!4ML5z{=VbRjkj5XO$?S6mh9FR4=W1l^|h~|SuhqI$XN6e)umE#NF z7poIX64%jdeI!-rtQnqwD7R)7`Rzq<~DyKL#F`HaKdk@G;#jbo#l9jB0+=nD6VmgS?n zQpiO;$E@vYu%vdsyRkm@_MoBDZvLdWr351Tr1CTiB+wq^aXXM(z#v1ujz1=*DBRm= zD?dT`E7Cxyf_NiQQyVW$66%n_hD8ajrl-?62Cad+a1R-dapxa9AwbQ;q~ES{RA;4| z>!pU5diOhG084cB04K7dZHndY`sJK&=JSPXpEln=TkPqRk=n^H2LCa>H#-~-7crFH86z{>;r=&z_i3JL5Htk zzHUz6c7=dDZQ3p(U3M%nRA4j5kme>k$HIep(+-K62kS-3U-_*YFC7FhsbG1olep8% z%h>??I7@Izl%Kx#YWni}s3bKYc$pI>efGL(%Tiw@u}4EHC`NGSt-fb`yuSLk*a#bL zQD}~e_rpGd#qfRl6vZlTMU6%wtWX2a-b)w{kuy%Wu%J;h%F*>lIv14!F77gRi%{zy z8r@>CS zCr8Ou_L*83Rw8U{Usmr3lyz3`#&zS7A)0T2frWF-EI}u)tuolMW*PD8qEo8r^%T-B zTCqTRgC+$oz*ew|soq&Uk%*m1>8Kw~w}9d&o;-epI^p#-*iP0z>OWxhY+m@412h|3 zsWl%WcW^(YDYWMKAsFLuq+CWeGR$V$E!2ftG5Tf)Xqy_@e>@L=6fxg;TZMP@9tq#Xi4zE%zD%~e6fm%i)8Os9G)$R1z!|U^3gv8_! z=3$ijB0_2nqIXoUqmL8PbFAL5LEf*6v_^{N0rFzN31XjtrI#|>+BK&eqNJ|-p~tip z(%$;<{w&m)+W+8htdU#3%rBpRo)&oMUB|r}1X){uYLzy|ND(ubp-Cm40#02+iV9L= zr0LB^CAk@T6FKNBe3v+vC*sqQ)W_LnhF`3ukkP*Ar|8fMhqB|-0;6azQ#EuIx@c&- zp+h?#-!J&#bz#ru5GXSCP0HPF%u%U<{>LTrE@z4r2iBw^_l`JCV-T<_0DLS=xb4w*(@gkd!HGZSYpmMknvUj ztM5suHs4-=;YVH+BS!`Ctq@*?o2)=I#aw;JOy7MIDuHkFfiWi1%4IKb4Hz44H!6vE zTowe4U3UA%^*R*sq<)L>dY5m>(Dz9~$ZZ71k5ysd`D+0{`C-OLsY87N#3gua55gxQV8Q%z9W}KLe!0!xsSQ%_w&)Y3{Ou?l)5!LTC(mfAmWS zPyXS3kwlsA8#cI$;WK=U-Kr#gL9g0r>zLO8a9Qe|6Te1=qoSBMOdLz~PmnGG6~xgm z&BQNH%SbC!exXLiyd5RV0%Mt&yC~G~ zS%$`%)lVXniHJEuG&LY(rC}QwoLIjRv1u=qGliF zRrbLuPp)xJS=&WS%6>UM<501pLIc9+9Qc~`Rjd~10}6q&p*c|a#vLD+@RV|U+~}2e z8113~X{8hYE7P|)<*dWV=VB_x_CM?YjPtZTJ=tKGqq;}1chyFg5GN8c!qCRKhZj8? zW5eZ=#6iu3cn=p-Sbdc@1fLxMF^aWprL)XbCFXFm5?sTt*-@x%X?*8c=bAahoo5ru z?&t3$)dJ>Dst%zVg7shj9nKZcgpS~v{$d#akC$M;kDtG{Y}DX>an zL`N{6K~}mQ858fi26SA}Lk)ccwExal%}d^43nPfIxYDlOF+s`{1`2b{(y{8*PwaX8 zMaxC2mr0C7CRFvChPiw{ZL5sG${Ksa2l)5CppU>ftg|Zqm^=$DiUF(B-MqF6#MLZa zZQ8s7SdGNAl|-@^ZA6{Ag{w@HmDFp1{sj@$O7%-$)gpk6Upsl(0d5k?91N}g@Kr@AY0 z#z|orgJUHY1Azuh5Vx?WeE_UIPfMFQ?k;t#XYbW!4}-ga(L+~MwZt=mX2G^7Q(H0! z@)iI%5keH!y*lx3no@P*A%XU-|Iy;{N@26i0)kT~OE8rgd_wm0)6$|Vi6Pn_(#`9@ zyQRSI*t4-`7*+Eqr~e5o!opw&2#U*XAd)OB87aLTfwtFUVGW#0x}o@}Uo9lcPCb{&BJ_`6yCy`kBMCxj60|V&i21gOJ}Dd7d+g6@v==Mj?HwpInCh>qVt37R z(Jmm91{XfG6ao~h#tz+IaUN~2+D>*^#qxub5tx^x>|t?zLc$aJj7-Y;8#gIX)|x$7 zqfm{0GhFUI}n-#EyC9WS9RyM7PU{-)+j z;EVD??4xRQ5TKL+1d>9GZ8Aq|jo(?&g~bwmyzS~RWBC{8I*3Xu>aH$ubark}2j)%TC@s_&2~%% zxD)HxXU|sNOjXUjd$#CEmWk9kg$n*7CH?^i?7a}wb&(Uz zivMnxG{Gc)qU*q@>8)?;Ey8+00@gl$Y19;$ShKUM%Llv=XS8(Yw)%YqU=o-8;n(CF zX?xMbvG}Z#t)eos!zr*e8^2i>NAb{y&43ec0`lst(Y?ST-9Zti;s8*XeVS{+J`XZe zS0cV>(AWkTTtGSF^k*+2Ncbv%zyzpVN)Fru>BGo-3T|ya3K+=NX#xu90cvN0t6^YD zZ-T9XHk7ohSD?-(1Yirx{%&Rj_b<0tAE_b;2?~&p3;0a1Cv^fzzy}+UDWT#EsDQtd zZWb2assk+t1!jV(T!G>AE|lm2~Y&^{?zZS>!C(H)kj`DuucI3 z<=Er|acmWTWAqJxCMY`}+1g2Hfg`(FwR;Xlpz~Ee?;~vveJRHSerbr0-+wLfT%_D-X2<($wO{lQvI6 z^x;oT|3q*r(=OJno13fPW7g|Jyd@Jqe*Fi~@FMN2J0or$leNFn2pEpw8i?|NJ!Dw{ z-TiF<))6>`2M0EZfvbUlOLJ&x2;4`AtiVX8LR z#SNen2L2Cz0?znCPYl10oa%gqbiiD~l3xANqjI#<|6rrHRY*<+#=4`I=yyv`t5D|b zfH*k(>Mlz3^d#8*a0EJoIXwy4CX{$Z{Tis04+0|2ymi-yD~ zcj9mQ{qO+WUe?ZayO5O$zJ~`seHDYDEhk@ZP;digbScpwfe=aFJxBKet$Bd0wc-;q zXbf@pt^!M516Ncf6*nQzYLe#+^vjDha2riq*y}*|@Qh4kzzWA2;UW&RM!U}?CR6b#X z$2wSD{uTg6<-S%-7BfChqOycefNiPF5S)eKaH4}^W0&&70Ar6Vjc#5tiN1seIRu{} z$m0*HflrggLLgf3a|Tj(fR(@;XLA}_%)s=SfV2|tg9)YjP~?6_5Yx061m!O?8zZ+I7wu8`wp7{>}n$`wKwQ4Tw9i)Xs(};60oKf>5tZz|)X? z@QNfKYzs!%=^|NB}%mgvZIaZA%@xikbOs+lT@!zV@f%Ez7BX!%gQqkyob5#<5+_dC5^ zARdj5iSThKx)C#pfN_2}5x|}F7|N2fc>qCA0ccbP^p;&z%DIHl#^3Ow4q8E{U!#Q z1kW`H9Kut1ogq_AAL7oAm+U*!z*~D#L4}e61n0FSgkcE&1Kc5(0v@p@U=Bdg4k%U? zWHE@i5>&7d6g~bsG(!@vYOHWJFlu-qVenh!2?MQAr6Nie)VmPV$0FD7V!wb%K-hLL z?!XO9l5!GwrAqr@*=KsJ3c=U`^BWNGkjR7cYDTEx1BsOWdBVF7mH84g8qhzSQf;rq zore-7ZdL6Iy1p;f|Zv2Y2{spi}cj8088A&Ay)Gg^(9x7h(E({Ibel z$NDwSMva4@PheIc=boe-=lqZ3b5JZ8n9o#gAIGuAZAfwgK<2Eaif$WFQG$kLno2Ii z7I5N^`8xIaL!P=1bI}pLNB%PExk>8;A;6F7b6Q%v(JSnW{IFLsUgua8LghgY7U6}( zi+}8L;!pG|Ocdvz`?w>ijXqzKEtB#@^}K8^z}A&BF{1^7bAj-<9Zu+<6CpTfIB4DE zQu;4;%zOOf7IF72oC$d*XN>rHu8f+IX_1p^cbl2=slf|i>&ChGA_5n}3gD2tw#3gl z)#02^HK%hqJsqSFIUBO4{WYo85f;wb6T>ueJkHMnrTiXsc3vz1eF7LI#PoN~N@p*Q z6~Ez#gN@Z`O+bZUNNxC|$F}%p??VtCao}`o0}Ca#;r411`_gyx?6)yPaJqt>KoW=* z19~oOfbUaq+Qq1`D2NgAbRy_suWgb!slElRhC=?m%PwSW|LhF{vy|yLgu*iTH7~dI zSVD`hYH}7+ajb+(G7t{z$cXAd3yP4Z&dyOGbe9%p6hVVTPx6E}`}=}2TcBW5jNdH? zwWJ@gP7F0ojuU#Apk3R@Yrsje9|>0WgF-DV;tB%vB?h#2i9YEdfS76(4jbcoV{EoBN}P-ympJl*B4D(D)cmYbnQ_t7lzx&A=|uO-s> zFl8SGT!~Fi6|xi{ND=)8LJ@AlF(6c=&t8gTQE&m48UbL?2WWAJNr1F4p#AacpuYVA z6-GGhNZmi@3I1s&7pRg5gn;U?o95t**Gbkvm8JQ+CQDxc)wu$jQ%7K~!49ZhsR$bp zIuP5q^9f*%b--PJZO{(Zbq2T@I7KUhsK;Jv;xp_1wYMDuboCp369RQ$6u%dUrSuoB zHI(;IyIN+j!F51Ys9zp|x(NId#D_QF3izE}=RF9kUAXGH zsau}Si)tizu0FquQZnmI6v)%D4w&xuYIA=RVj)cpj8P(&bRH3C*+Zx-!En9Rk1DIJ3nR<{BZ@MH{n zPOt!NM|_&xqyMdkyd64Vya9v|?^`&;+Lmi3?mPD{qUd%Zo2o61+#9PvvuiqKrdt!| zjt7hMP|HX)3^>7q#2Jw=`o46Vr3ts+a+!z5f^zG{Do*DJTd|yO)7kX@O_b zKfN>Au<)%;a)z{>Mt<+B-46@rJUn{5f1SvIQw}^90P{aYH=Icznt$tLvX6R4!J@y@ zn8QECx;L2GoBmx4pVt7*&fokH0})JToen$hfzzVBQbTvYh(d3;cOqN14;y0T4&lN` z+bXvk#AqaVo`{n8U-yk3G!rUsfr8BpMxLSK7sp>-06J!Ul{X>QJBeraAx8jiA)~ zs2Q7W7bHL%9(7+o?dSSKpB!UbG6`2e65M)8e2m1ntpon`mHhkr2YWK?0;8Y3^ z1_u%Box+K@_pF3om;IBc==OC9f$V;@=|&(hjXnXG+PmNw^&%d0JcV5o*9KwVm=XNM z380x#|ln>Am9(FbSZz`0p%0xQ$Xn549VXQ|5@;WW2S$Cu;LDzzDQbns|sX#o1cnNMugc)^?A=VmJH@|B9Lb>wu-A>RyK3{wQg4!_Q>j$Nk`Tx-;8 zz0?p%QhddigVv=&@m5b_Tjgi!fkDifYf#&^9A{uZ^`IN=xhh57+=juf9IGoGUh-gA z!3?=Q!XUOL_TzAphL(2o3M@AkJncH2KBdA;!gsy>eWD3SU+v0MKtzVj39%uC)j>gj zNi5C;oaZ;l8A^YIzstO-I$*G3$VX3UR=sivyj~S_(g*(c5LWAM>X#ESY1OWqvs`V1 z7c2FQ=YT6fi2-=UFU^Nn1i_!%w40gW@iI*MwcO67K;Ueu?aiDsLEtx2L3qU!ukt&f zh5|`&@!A|!-K#Cqs}4>BYQ%JY>)>|p>Xb^OnK zZ1~bIBKi&Cg4q=YHs+ys$P9uR$ry;*?D?yfM)PKc3?0FFx?}s28kHM3F!$n9oFIYy z33$o^Pp0qP2IIat-%;&T%BdT6OoG|AIlCa}(dw~zXt!Qsr^DwPf=SQB?vTLiMy)2G zj|oTAARkwI6@v&MW0Kn;z~Ht1l79O5ybxgjt=p%e&iBp{Z6ef1r+aG)pJKRHST=Uk zyr^a_6K(3B$>uuG8Z1Fe9;vWpLeWA|azojY_lzzr6L>Cs#<%;gjo^C<)7caT6x@6# zL|XcjXm{$kE_U?3$=w{J%klC>X#|lE*JgfAk$%37{4{lE>wNGnz-d($+bo6V-DJ{8`NZO|H?3#i%agWwm z|5UY?{g2E~ea{(PLyXtX)D(Q3@4b^yt@WAs1Jr-Zi%r&GO!nZHLwy-n!CexKNx&=w zA#O6o&TCu34TPIahQY49)j^Qo=8h9(W>ZXj_`a;y4U9J^lQpM910|jr2R~NheY-(Q ze|gncrq8U4O6^hA4Ewq168T;;RLzI8oVj9*7;|ac_r8_9+aozmzv0MR{%ZdY38%V9 z4e=V=HK-9bnFW|CXHCL8NFIk3?UTXW0h1a5(ZiLZ+dcjHuiFU$otyT_c#ca{((fe#VH zry9P$qH9w6(EII_+OU9N_QXS5rxhzb?s|$J<`X#-`j*KTBDougUh(=boalvQtMO>B zIUfVaV3u!@@JB|AC0geuzC6d=QA+rAxG~mP&reXuZ@ip!pTcjq%2r+ClX+xv-rPIH zT&*R>Ct*Clp_}6jtG?tHGf4a$0M>yMm_y3EAeNNu2kE24Z_h zcqWLDl*^U7Mpou~Ex<0(yJ0lqqtx63x-S_&5ms#iUPLb)8L?ezsqfB%#z3QsZWCbc zw*PbMa{&plYAMQ%$1(D(@1Iw;`ZnCIqvw6dAZUMqk6zQ8_?#$HtgZIiPK;gATy}fs zS(c$Q$H)oKi6=k;1#6E9|nd4@E-Q$0pERo;?)S@BDjUwv8ek?sq>3sdkdb$3SBC`{4ZlfRMV z&TlV9s5z5+JYViKX+dsdsIzfsvQ16S#-EUZ5CdzOf4bbw1pA9~tHP-Svs-%%7-Avs zWaKAtRP)RHq~3K+u~a62g(Ld}tD^KyEj=$>OE5L7=Vr`SYl4={4=P^umMBF>4xBKb zt^;dg;Fs20UPOMvz#3>|#Fg_+mkvGOBB`Bk^_iilY}fkc?sw%Te3z+kg%tG9QGb>{ zi(c)xAMnO_O$zaYEp5u@;C3hNrj!@kqaA^s)w4fg8A!NT>Z6`Fc_Cg)($JoYcS!2J zH}hhE+6`*XC(dE_-`Hxy-Zc*Eiht)Pw^UBf*8O0RQw~HcW$+K+P@==Sx(F(r8$QZF z#yT2-Cl6HtywIYU{>hX zD3HUPb&Mo&FMDZ;-Jpz!spxogF7um3ClnxPkb5m#8M5 zIjteT`8&x?Z}g=Q$SN-D_x!CaHvBWu!qOGnYEg>UGFHa+zHn-rldKDj?r?h%F%wLR zY=uwiQVg@csASmsLxPDVt@Zu-U~#AuVgz8N|Bx`BeJF%t%k6`%;qNsV+WZ|jxlq4S z*OCw7=^G^ZNF@Ml&l1>I>lb&%GJ>HssW~!~x?_l{>85yf`TE-1CP=h8LPC|Z)rUqu z<*o_XAC7d{DqkZiCMSw5=1)m$3q6N$!Ov5kYtFdA>R*~r-V|0(0RmBX>KU-#Yn54a z_QW6#giDlM?njo~COW71C6;OAXERhNPwcJn<|^if(CTx%85^Xvo2@CvW5!#2UTj_) z&#O(pr18|s+Xokf(!MktT(|82R_yg*unu_Z6QljRLh=S%Gk0D>UFQ12XC2=mA%s}J z8Km%#v~AEhVUlapyjt}mnONNO{EV~cA=UT^5}fvuY;fcKX-`8!76ESt|M{3%XBcB<1;*?kk;58(}b0j5jYRl27F%f=hB4^=64CU5mP3)ZkHwOgoAtZ5tsrm2oTR9SPrG-ok=hE+Nt z&?yLQ)^!6kEfm){&*}A)^U=k2j_`aQor4xl+Q1RQSF$Y2OcMdwko?mD_bcEbrlUl>hIn)cYIrj3Wyxe_{rYqxr z{FnxtF~l7_fb~E4d2$nnbSvlcY!;@i-EZUM0q@T~I$|Lb@LU2$LvKH6LbZ4I= z!04iN{zr^xVinz&UKL4h?US{s>X7h#=@{CDH#(Je?4G%pd{~MQJSPZ5!Uiur@{e?Lpb|obl8m@-g?CkqSNlPbfp&rG?e6f>`MC{fVJa_J$2$MKT z4_%G-NjTNGCiB1|#+~tX3-Hn#`zlB7RnH>ub3C+eeKk3KvIs5ZSLmLw^VE^u78y*Pe4PO{kA7Wk*{9v#oB^OZ< zr;pv_*0zm*GJN1&d4KJ$gZ}8%;`?i7>f%GntZ1-P{3~x7Om8sS#U=;T5t3uLe9qBS z_=Z3uh#{0Yv0fj{m=*-HF6V|`&7jb6)^u#lcBC$TrE~5_%$eMTC-*^M%+em+BFkI*E%AL3zP<#3o8B6AUfi@`DmKpyVF&p)?iEOE?%3HYGw9|}DX^e>9 z)JNX_MgO#R*VSV5tA|Ov+V|04fj2{63o6*V55kRu8~yG*-uF>z=r!wQd-$9YO4;#g zsYIWyrK(Z6DBZf#W4y-cP-7xUeLdyw0n_XRiNebbm2S05rKhc}e%jpHU29V{yEE%# z|4(~Y{twmr_D3lqG%YAwMxkO*w(Mn?ETc%tGRRbj?2K(t$do-IW6fCV6Cz|8A;~1f zAX9e6+Gr3W>vIo%zOV1|4?I6T_Yb`?=Q{Vf&$VCg>ptgj>Qop+KjNW83B9`M?$9Lw z)>qI;yV^6DJ78z6A8bogf#dA?EuX|({*wlz>U*@|DfY>+!wWC$AH*CVAFvvOXN^CK zJ5e8s%FYmO21%de#p!{ZtQH;lL!wS|dcH}*0+aCLVz@UamUQ%MB{<#Gu2f4<&xS9` z4UWMfurMWkpLmdY`PlPjzZrO!Y8{a-u5?#H+}a*K{#=9SAraihY1w9Uy_i}gzHU#6 zOHvH667T;SBW!;V?y}#c0baVRI8Y74!i3KWI5UYM7ct* z4WcoeI8#Jb@qhCWW71QUUE40|d^K}OLj6PV>#=D8fb&0R^H6d;XK-(MjO;u5C+Z;Z z3a`pQ+Zy4iTb*jbV)A$i!%z{P(vw$3P57)Sg7|0LOR-$g?(pjt(*Ks~75Mpe72P+7 z`uzJ!I#3oP>b!{Ytaqze?w$o;h{D6S<*8*4J)aa!mpbI#>-Iur=0Sh0e^bMnnmg+D4+@WL(tm>1{RX zQ~y(v*K?s6k-zQ4G@F2v3>x~5_D>^Yr{J(J0={_n$1NyDfGu?hVL7p>Zh8+vuoR= z`hK1G!7fU<*&r}}x+H~v{@$(HMf0OE#2L>q#wd7sgUwyjC{Mmpp2G0wTagn(bv~}0 zq34&o!s$xcepx@!crjFKijE(3-qo0K4&j;;a=lQLP;1?Vu2kYQ8Pr}aKRy497+Q>H zb8{`+=TKgYDGv~fsEYiaeBFT->yV-CRW08vgm3{!}10BLk*V;ym3m` zR$jkY$f!ZdT#aRab6`-?)PGv){PPt!VZK*nbf-g&10q z;`%XGJug!U?;VGG~1T_;PlWG^y48DD3oLAR}nqmKg@#w>XH4SeFe}aC`FYx$@89 zI|cLXB$Q0{_u)6(oj}2+N-VlKWwJLrbPuE^Ib8*x1~1k%#Y*N6G;yb z=Gtl%4sFn<-beLt_r&F>#q)%v#)GRVnjXhch07aOtp+pCb6=kMURTHVA%2#U zwAGA;R1hZN!%*(gzCD>64O{oS9IS(0De}kkh_xAz=3PFNE-tu~TUqIP-fJaRjiATQ zyowJRAQxsH8Ha~GziroZdmJ-l8Vn{AP({4&_5J}<}YLXa4783V4zh)>6Jn-+sC_A%CY{MBIPx% zI+d4M0(vOe0(*)fVoiOZZesrD(E|MP!gX68!8Xrt7n(eL#?@ek>bqA;9J~8C%`c0l z=Mk^J`X1NwmNF}~R2z5{)lr%hKwt1(Sr`wD^zHyYV~@aoWXo5N`SaD~s&PU;96as1 z5-vs7L!qZy-IIbQD266g-)^%w%1ymky6W^{OSGtgvY+H3*k)fz&&&^XU^vOZV4V%K znp9Ur+E4#^rFWGD5>A4;xSP?aFXr%mTV+CFQY79#mA9hmCqW}}qPFI>Q#Ht_%}z3U zUv#Lg&ik=U5#e>1LZzyj82qK1F{QuTi-w>kThp?H<(Et6ZnVu_!@3_)EUov3XZLM5 z2p?a%C~mxLkMY#*)muF!u3UAh5M2;_ccom@$mw|%J;V-#l-U!YkjjKBNfa%d*r>tF zUq3T2MaAS$#R`(5U85+x+k8~H^{km* zG+jHGs_8TGt?puLHVMhIYte!(nb)fXYJB9D;bgdiEDKk zRA_%lDtZiloY*C@CH?NVc(rHZjOK+HJpQXkiG~J780GNGF7u<;EwPr@g|&H`;wONk zSAFEd=)8sW?@6mfp)fg4$16+N1gNeed}4h)?+e&Pn^FUPnq1MHVFh>wn{rWUZQek# z$ZVIb@;|rJ9OgSIy2+G{^ajYgZd%-WulKw7V_y0R_*mDY+u~pDL+lxUy zg;j{Y^Z2Sr&#Br}MDN6nxLM%rpXRoevo;5N@YSaWuFMbZ8Zy8Lk}3V{BhOit&R(h; zq&Wm_-0ZrRvvAy#ui-<^$K}ga^emN0ieN1HH^6=%^)7zoQKBzxp1k9(!^CJQy(HuFqur?w=zN}!SjvL2MR>t3-fK@!JgwrMJ->aub zoa@1gZ&X(cv#7w;wMD{(_hBU}S+Gj&Xsx|wHiN0WZhX_i>rM=nPYk3$r_r+c{zQFW zqASt61rv};jI#WhH9 zm*D!d;l2HrMFNiC*0Djw@7)$f3yc@Pqs0R)BSQ`hzR>kIm&Jv$0jF!A8dw$4ReZ^G zKMS{ohNG}gJFqse|Ek~niq!jP@bs`HDG=gcpJ>9+a@)y>OQp9ibyCr17hao#`1?rPe&$n{n< zTB1~|(c9Ww5N<{vZz>wzg!WI}Up%PF-R>{1!S#^X_vQX=HlRmpQll)3k1;b2Rgdvo z94_@l009&uOZ)e9pME!K)Ub-M=|6usMMJ=UXfb0>7Y9m>tf0a@uzhAQ0^4||g5>99 zpNQxW4JMiFE{m54Z#)k(+HuPi@650A@=zB4lR_B#1cN%X&bj$kxW8|h%q$JIS~3UV zZ4nPX<8x%ha>F$>XTs9}xpxvZ#wle2GoB2U7dCX3=E;{sMq;CL+>>p_ab+)-Ph*8< z(uQ?;%5{B%ThW~6HGpBRK(XzCSYfN>m;)ij&AF4{nbS))tZ(lC%t3u+ZXEaQ$;zc& zg6VI$b-oDC)!{yE?N!n7B^o8TX=6A$cTwCC>jV<-o0WUAg3-~pUSIWJ**Gs)(s9ja zaM{YDzG8Qors4b3msIW)^Qi7+ad4D|rFeZ4$t0RvfzqDc>tph=T&zoQETOtYr!e64 z+%0TDr~nU#PG0$AcyL5L&puaENt~b1WKk&N64#H+585U+R=TBH03&0M?NYIO&zkO1 zvXB94T(%b&)9P6@a4pJ-uzZNW#66D`#JTAXTvlI@(0(LYv8>+6kVqPO?rJ#j4bBo{ z^!<7;=54q|mPLcWQ+;y&v!wc-{SS%fFuegI7=E_iQ-%9f2$4%9AkbdF%YC-W)t8nh zhdihaMuCF+kw{*y&j~)m9IasEn7_CtN5Zq}DX<+%Paq{kXyum%JUf+~pBCijYV60? zsXDK0X!YWIzJs`nT6JA~kEVJk#j-)*h=I&empjhadVg*hC_jGg1SdKg)s$#;qX>~- zRbwai00=}h@f6D7?8#TEJ&}9!W)4d!L|Km)?G8~h!TSiJ@Yk=@3TPlp#e6eJ2d1iJ zW{FNnsCBs8vQc@S&G#CUOdGZjlv^!y?$wivNprg6oo$98p@l%=3m|^;3nx~OR)9hS zWS$K!<%Gz(hZAY^^pn;+2c(Xfo(LC1dqUKcE|xv`)~FVLZE-aU?HZS z**2ZK7mVdO!xEhawEBI{rpI^&7xk<(M2TWR{#o>v-0teH7iKsO)Xtc)p)bH?4eJc!`spPBgWmjh~Oc6E-E# zrT8Pcs3KF_mLrSWY1f%5yRYyTorYP`&4Qe&H^$if=mHkej7ALQ&i?u!i>qa&V{Dgw zf>8<4t33{t7g2Vdp0U>X<{qZb9#9ynoLdsJsj z>xMgIsA0-hG!nH|DYdBUkfUiqhZ+PrkH*s`J0km%y&W(!>6|}0INTDIo58y~n;iAo znOS0Kj~vBcxX)}XXZG;$imUHd9t~&>JlZV{;mMuPhxCC-AH-eaG2G%(MS(oDR+^Rb z-kgH~mGR2$r;CAVnOw_UyXNP)_8cwxfe5F-{9Y<4z>_D%cXxfBJQRBnCG+LoO(l)+ zj=iSzmbDu}ej;=|pWHxXP?UJ($hVfq?C#F!`Gi`_RLRB4DXEd@jBo7jfl(g9kEfmi zu0HW0tQ6cMUz0~Y$^?cI51pCO_y2yBT!FSL8d!5;E4Xu%&VOg!{_2Y!1;%ELP^Q>u z-5#si!wsfqAd0!x{UABvBAT0?c2D+06=nOyYz)13lZW<(tO7=ZszWol^+uB;Vtsua zSM%qW#$(GD6D}5_+yVw7dH?7QO&@gA9KQpRO2jg0sc1J&4bYP zH@sJ4yBsp=?tl(g=45J}2NlX7rY~&c@$$cyX9ABwyJTiDwGqL*0ZEJs*X*jH->c{u zwtwo#MM;r2<%a~o`)Hq35G;@Q4Rs>n33GetG8OLfHf}V@HBJ{kdHLTt-eTqaf$zFj zc)wMCvf^C-P##dYu<{mfXe1xmzn`5BZdJJdaOEhc{=x+uE+~bM$swEK~F+2VNb{_|a z!&&9DTY_zq1z`d|-lBCH&2#u3YN$z4aMPQzG30lblK&AZCQv)Iq;8eeYh#hlVg6*w zz}iCK25r-jd)h)ZYC=UocR{WH>2l#H;A8)pNaw*4q42<_MU~S@yq~C=NJ`;yL3zu{ zCa&dS5(m3$+*J-w!KMoP@zho^yHf@4@2L!SMLERW&WyM+rqWunxuFr|IwZEXt}gSd z_GFE*_z2hA?61zw0<-VpBC1~eF??O5pZRi$Yf18l^Yt|3p&n(<$P0@I`bT@*Ku_6J znTzoCfVRBk_^o783_H&N`fKmIj-cs6>5h?2LvI(~p;hCqYW`e>mjH#4$8u2uw?Mpn z?{fIp(JuN_++xPp&E~;d!698MZ=a7B%yR0L>$jgsXuXZ7jNN6~b3X&TkwC89(n!6? zk2?4@z$d;=2DC^HZZQ;Q(2nY%{b5QWcb#W0sX1?qS<9$NcbhXfg zOgbxC>o)4-&=m+xBWf6R%c~u5NmccLobu3{I9zO3@Y4X}o4CSuv4MP&N8xVB6xbB# zQr?gdVXS-EQ~moItaeHDi{a}BF3>@U%1trR^DY}^w8}wm9`i|xJilUk`R1z5s`*`w zdRlJr1<*giG*-CJrxpo_)LEwubl192x2hJX_f$v=?fu?ib9<$iYrcpvu(2673z;%A zW2}%>XCkt5@Ivn<{T}t5Qz0K-5#3mUE%v@77IuqeDnWWl#pv}Pr>%a=4>(?bJ>T7s zEU`{J16xIBAKCf9MP>39KzJb`g`nZAb+#Q1wzGoKjbM_h0xW6g@BYlWy$~&IzgN*j zEhsj3eq?s0AstK{NEXKJL5&9}^M4=U$~7Fo<8Od2{Px(P=K2_>1Y)&0g>~ zKjwh!7qpf~3TcP%MKtqTN@}1u@`(Rmzl{UOC5OyIgo$0le|hc;0srw010kXvt=*CUoNpqD{rBA`0AUAE z-uC2L(aag<;htay04oJ3fc}%^&70!e2VXn{98$B^L+TiU;x-7x3wMNC3mVzt$Jn(^ zkaZofb{`LAtB^5j=yvfevzxr-+_~f!f$UN`Hu$t z*g^kTApcZY!1YPbH^GL0iK<9jC1z8ZgVPn{>6sqXztf!s8&TiVKo3#?lvTD$9O>2b z=YeFHHrTWbLa_@3=6{rzKUp!X2jud_|3)dpB*8=#-2A-f~bIbUYi5djp5 ztN_B0U#F{IXHJ=^zMnU6QuChM4;DbK{h6jyUspLnLcV~&*#d$l zIQ=h3IVTHzhwyEq0c8rECn>d)oi5sO8a%(l(tvLjZ6dF zzRlQC+AL1yeXfB!s{9C`H;|{YRu~}r(-7z6a!q3lx0xCu4g5{WPq0H`m~HdGu%sD> z3wWcy`Gkp!CqPHPc<}A89u2m~KrBH@2?yU^V5kIXg%Gu#vMRwo^GI$JXkBAoO6jh$ z$;A-j@gsYb;2=4Y!h%ovfYEUhC|U9D&=Ch=Xg+A0hiU@zU^HF?U9Fx!y;!|Ftz+3FaCrm?{+kUKhQ5x5_tx6j#Jl0WYhzOsIPt zDMM8S$P4gudtNO*@T3F8#~Jj{#YX)=`*m8LfH4KO+Nt1J-7G~YHbe#Kb=}%ogY-G( z8eTW)@q$Onz$pMz=se=s+awR$j9Gmkkhy2a;BB$YMUa`E4H4LiChrymz&fz&5(_v0 znqQi)E`e{HU{ehI@ULE+3t`=!`>PxHj>gP;z!MN)It9^0p0Pm zt3?Z^U`EWMigEF`v{3ZfN8*)~+#xe^?lxh422-Omyr)(Y=~g<8dR}Uu;&%ylqj_?5;i39hz0-7M6)DnytRL*9rJ8->eTk7uge1k)ZiXexffZ85F5!x~8c3v3j)5g4|yKs~Y`Kw7-J1ZRf)5K(|fXR)H&2RrNmkFKz@ zaQ`-R+xZj~2h%L~K!ng8RiS=hof)j_H-IZE#RES;Zq2=t(Sl#m`Fqzt?7+iTrohIch$#*8CtOb+9>yRH z|BF%e8%znafq(`!g+IcFw&oTG=Yv-)qHgWT=QLA3Lcrv>#YVxq`#xE5thpaSIbf1V z2euhK?9P+|rqlQ|C{Z#h4*GzKJ?;w|GH3g!mJ)MzBoMEjyl9Ms-wpo-simiJ7kNQjrB|JIp0KKJug`35e!W2vZh1~VrR)kOoiF5 zCZd1~*o023RQTMWIm?315ATlFbzcCs;2U@S8BKCSt=;_cUNfkB&uU6)!OjF~ApL|C zD}dl7G^QLS{>`0#>GIT#2zhvCyBZA63Z60qBjg^4I}jguxXMEcs|t(|LYDm%q1y94 z3hz1+b$ivR1=QL;8(aIgiERS_uR>rsm>b-d!H)c>PqdN=fnb-rI|_N_@ZW3+%o??s z@HY_ze`o+d_;-A|1eUxrj*I;lIhgnFI13V;zvKUjA^*>fkf{G_-I&_it<{9 literal 0 HcmV?d00001 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3240a49 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<ļ½œendā–ofā–sentenceļ½œ>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<ļ½œUserļ½œ>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<ļ½œAssistantļ½œ>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<ļ½œbeginā–ofā–sentenceļ½œ>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<ļ½œbeginā–ofā–sentenceļ½œ>", + "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='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<ļ½œUserļ½œ>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<ļ½œAssistantļ½œ><ļ½œtoolā–callsā–beginļ½œ><ļ½œtoolā–callā–beginļ½œ>' + tool['type'] + '<ļ½œtoolā–sepļ½œ>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<ļ½œtoolā–callā–endļ½œ>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<ļ½œtoolā–callā–beginļ½œ>' + tool['type'] + '<ļ½œtoolā–sepļ½œ>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<ļ½œtoolā–callā–endļ½œ>'}}{{'<ļ½œtoolā–callsā–endļ½œ><ļ½œendā–ofā–sentenceļ½œ>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<ļ½œtoolā–outputsā–endļ½œ>' + message['content'] + '<ļ½œendā–ofā–sentenceļ½œ>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<ļ½œAssistantļ½œ>' + content + '<ļ½œendā–ofā–sentenceļ½œ>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<ļ½œtoolā–outputsā–beginļ½œ><ļ½œtoolā–outputā–beginļ½œ>' + message['content'] + '<ļ½œtoolā–outputā–endļ½œ>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<ļ½œtoolā–outputā–beginļ½œ>' + message['content'] + '<ļ½œtoolā–outputā–endļ½œ>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<ļ½œtoolā–outputsā–endļ½œ>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<ļ½œAssistantļ½œ>\\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<ļ½œendā–ofā–sentenceļ½œ>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<ļ½œendā–ofā–sentenceļ½œ>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}