commit 13792b1125e8d6d2aa51bf06fd951a24fe9662fd Author: ModelHub XC Date: Sat Jul 25 05:55:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Undi95/Emerald-13B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..52cb3d9 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +license: cc-by-nc-4.0 +tags: +- not-for-all-audiences +- nsfw +--- + + + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ZBzF77-1jKc4sC25UY5DR.png) + +An attempt using [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient) on [Pygmalion2](https://huggingface.co/PygmalionAI/pygmalion-2-13b) to get better result. + +In addition, [LimaRP v3](https://huggingface.co/lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT) was used, is it recommanded to read the documentation. + + +## Description + +This repo contains fp16 files of Emerald-13B. + + + +## Models and loras used + +- PygmalionAI/pygmalion-2-13b +- The-Face-Of-Goonery/Huginn-13b-FP16 +- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT + + + +## Prompt template: Alpaca + +``` +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +{prompt} + +### Response: + +``` + +## LimaRP v3 usage and suggested settings + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ZC_iP2KkcEcRdgG_iyxYE.png) + +You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length: + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/PIn8_HSPTJEMdSEpNVSdm.png) + +Special thanks to Sushi. + +If you want to support me, you can [here](https://ko-fi.com/undiai). +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__Emerald-13B) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 51.39 | +| ARC (25-shot) | 62.29 | +| HellaSwag (10-shot) | 83.69 | +| MMLU (5-shot) | 55.7 | +| TruthfulQA (0-shot) | 50.94 | +| Winogrande (5-shot) | 75.93 | +| GSM8K (5-shot) | 12.81 | +| DROP (3-shot) | 18.38 | diff --git a/config.json b/config.json new file mode 100644 index 0000000..00e5e4e --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "PygmalionAI_pygmalion-2-13b", + "architectures": [ + "LlamaForCausalLM" + ], + "badwordsids": "[[29961], [14352], [24630], [29962], [11759], [15974], [5519], [25473], [18899], [25901], [7110], [9341], [13531], [518], [9310], [2636], [3366], [21069], [11970], [23098], [16733], [21298], [18173], [10846], [3816], [28513], [15625], [23192], [28166], [10062], [1385], [11724], [3108], [15555], [10834], [10370], [14330], [1822], [12436], [5262], [17094], [10725], [17077], [11424], [4197], [24406], [13359], [17531], [24566], [23076], [4514], [13192], [19942], [16261], [7072], [6024], [1402], [1839], [2033], [13970], [850], [5913], [28895], [5387], [8308], [24927], [5691], [12940], [19997], [18959], [11287], [16862], [4638], [22322], [29861], [21251], [14704], [17548], [12452], [17288], [23160], [24960], [8219], [18024], [5539], [7464], [27865], [29588], [20068], [19660], [27706], [22896], [24264], [12258], [2314], [4400], [5586], [12622], [6796], [7226], [21939], [18456], [14178], [21540], [21945], [14664], [16215], [10338], [17361], [7503], [13769], [26073], [9601], [26909], [7961], [8999], [20840], [16272], [21545], [3199], [10514], [5159], [22689], [6525], [20526], [27077], [18017]]", + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.33.2", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..7a03f6d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.33.2" +} diff --git a/pytorch_model-00001-of-00013.bin b/pytorch_model-00001-of-00013.bin new file mode 100644 index 0000000..c942467 --- /dev/null +++ b/pytorch_model-00001-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92cd8908d77c0cfa46511f26cb666f00eaa4795a11557c22c428068575b7856 +size 2089337041 diff --git a/pytorch_model-00002-of-00013.bin b/pytorch_model-00002-of-00013.bin new file mode 100644 index 0000000..4df1c22 --- /dev/null +++ b/pytorch_model-00002-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5a0dcc3af840243663c25b4b07ef0b672cf3b9f89c9d199b301fcb90bc457c +size 2044815083 diff --git a/pytorch_model-00003-of-00013.bin b/pytorch_model-00003-of-00013.bin new file mode 100644 index 0000000..cb328ed --- /dev/null +++ b/pytorch_model-00003-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1049d1084c4e30d3e58be512b0587427e6a34486dcba9a522028e83617dcde +size 2060523307 diff --git a/pytorch_model-00004-of-00013.bin b/pytorch_model-00004-of-00013.bin new file mode 100644 index 0000000..d6f6d20 --- /dev/null +++ b/pytorch_model-00004-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08814a6d8b678dbb761b10c1f0323afbcf50c1af50bf4b1dae99a08c64899ea2 +size 1955665095 diff --git a/pytorch_model-00005-of-00013.bin b/pytorch_model-00005-of-00013.bin new file mode 100644 index 0000000..4b6b404 --- /dev/null +++ b/pytorch_model-00005-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e84674a92404852455bb897ed2f4876d1c94ffb78b645a7ca5cc9fec8a35f781 +size 2044794055 diff --git a/pytorch_model-00006-of-00013.bin b/pytorch_model-00006-of-00013.bin new file mode 100644 index 0000000..db6c007 --- /dev/null +++ b/pytorch_model-00006-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1a07bb8db5286c41204339bc04b5157b403b1719a493e95aeb0e9f4e17f262 +size 2044794055 diff --git a/pytorch_model-00007-of-00013.bin b/pytorch_model-00007-of-00013.bin new file mode 100644 index 0000000..ef1cd33 --- /dev/null +++ b/pytorch_model-00007-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa7d93e087be54f694b057dfe3ae1287a3cbe6b30f7429898674fd5b30fb609 +size 2044815147 diff --git a/pytorch_model-00008-of-00013.bin b/pytorch_model-00008-of-00013.bin new file mode 100644 index 0000000..c19c44c --- /dev/null +++ b/pytorch_model-00008-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db19799bb1a904854a923fa3254d483c4373d598a8ffaf802b1a3453e8a565f +size 2060523307 diff --git a/pytorch_model-00009-of-00013.bin b/pytorch_model-00009-of-00013.bin new file mode 100644 index 0000000..141c6c6 --- /dev/null +++ b/pytorch_model-00009-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cb84af975b857987098e86c53077e347f50b5221f34f0dc29880f8e726c0ae +size 1955665095 diff --git a/pytorch_model-00010-of-00013.bin b/pytorch_model-00010-of-00013.bin new file mode 100644 index 0000000..1ae318a --- /dev/null +++ b/pytorch_model-00010-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad790b1f8480cc8bbea11b04705573ada4c18f4df98bd440ba220cf16a818223 +size 2044794055 diff --git a/pytorch_model-00011-of-00013.bin b/pytorch_model-00011-of-00013.bin new file mode 100644 index 0000000..ca9899b --- /dev/null +++ b/pytorch_model-00011-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37f364bf95dea57032483fb7f420d29500574550ab8bfb553e0ba1602165e75 +size 2044794055 diff --git a/pytorch_model-00012-of-00013.bin b/pytorch_model-00012-of-00013.bin new file mode 100644 index 0000000..867c202 --- /dev/null +++ b/pytorch_model-00012-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c2d22e74f37c2cd8cf8f03264561f7742a2461bc9c86c72ac166dc8e6f112c +size 2044815147 diff --git a/pytorch_model-00013-of-00013.bin b/pytorch_model-00013-of-00013.bin new file mode 100644 index 0000000..67d0960 --- /dev/null +++ b/pytorch_model-00013-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83fb3c6905d08d6c4855e491556460bf052f0699c72c453ac19a2c88acb610d +size 1596514999 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..0bd7273 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,370 @@ +{ + "metadata": { + "total_size": 26031728640 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00013-of-00013.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin", + "model.norm.weight": "pytorch_model-00013-of-00013.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9bfed75 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..54c8ea6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,39 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "use_default_system_prompt": true, + "use_fast": true +}