commit 1781c99d05cc7322c6dc9c6017714a3937f677a3 Author: ModelHub XC Date: Tue Sep 8 19:53:13 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: utter-project/EuroLLM-22B-2512 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0677177 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 + +*.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 + +*.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 + +model-00007-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00010-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00009-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/EuroLLM_Public_Summary.pdf b/EuroLLM_Public_Summary.pdf new file mode 100644 index 0000000..21938b0 Binary files /dev/null and b/EuroLLM_Public_Summary.pdf differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..57ef84b --- /dev/null +++ b/README.md @@ -0,0 +1,125 @@ +--- +license: apache-2.0 +language: +- en +- de +- es +- fr +- it +- pt +- pl +- nl +- tr +- sv +- cs +- el +- hu +- ro +- fi +- uk +- sl +- sk +- da +- lt +- lv +- et +- bg +- 'no' +- ca +- hr +- ga +- mt +- gl +- zh +- ru +- ko +- ja +- ar +- hi +library_name: transformers +--- + +# Model Card for EuroLLM-22B + +This is the model card for EuroLLM-22B. You can also check the post-trained version: [EuroLLM-22B-Instruct-2515](https://huggingface.co/utter-project/EuroLLM-22B-Instruct-2512). + +- **Developed by:** Instituto Superior Técnico - University of Lisbon, Instituto de Telecomunicações, University of Edinburgh, Aveni, Unbabel, University of Paris-Saclay, Artefact Research Center, University of Amsterdam, Naver Labs, Sorbonne Université. +- **Funded by:** European Union. +- **Model type:** A 22B parameter multilingual transfomer LLM. +- **Language(s) (NLP):** Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Irish, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish, Arabic, Catalan, Chinese, Galician, Hindi, Japanese, Korean, Norwegian, Russian, Turkish, and Ukrainian. +- **License:** Apache License 2.0. + +## Model Details + +The EuroLLM project has the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages as well as some additional relevant languages. +EuroLLM-22B is a 22B parameter model trained on 4 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets. +EuroLLM-22B-Instruct was further instruction tuned on EuroBlocks, an instruction tuning dataset with focus on general instruction-following and machine translation. + +### Architecture + +EuroLLM uses a standard, dense Transformer architecture withgrouped query attention (GQA), pre-layer normalization with RMSNorm, SwiGLU activations and rotary positional embeddings (RoPE) in every layer. Here is a summary of the model hyper-parameters: +| | | +|--------------------------------------|----------------------| +| Sequence Length | 32,768 | +| Number of Layers | 56 | +| Embedding Size | 6,144 | +| FFN Hidden Size | 16,384 | +| Number of Heads | 48 | +| Number of KV Heads (GQA) | 8 | +| Activation Function | SwiGLU | +| Position Encodings | RoPE (\Theta=1,000,000) | +| Layer Norm | RMSNorm | +| Tied Embeddings | No | +| Embedding Parameters | 0.786B | +| LM Head Parameters | 0.786B | +| Non-embedding Parameters | 21.067B | +| Total Parameters | 22.639B | + +### Pre-training + +EuroLLM-22B was trained on approximately 4 trillion tokens, using 400 Nvidia H100 GPUs on the MareNostrum5 supercomputer, thanks to an EuroHPC extreme-scale access grant. The training process was carefully structured into three key phases: + +
    +
  1. Initial Pre-training (3.6 trillion tokens) +This phase includes the warm-up and constant learning rate stages, during which the model is trained on a mixture of web data alongside higher quality sources such as parallel data, Wikipedia, Arxiv, books, math, code and Apollo datasets. This balanced mix helps the model build a strong multilingual foundation.
  2. + +
  3. Annealing (400 billion tokens) During this phase, there is a linear decay of the learning rate and we adjust the data mix to reduce the proportion of web data while increasing the multilingual content and select the highest quality data—by making use of quality filters such as [CometKiwi-22](https://huggingface.co/Unbabel/wmt22-cometkiwi-da) and [EuroFilter](https://huggingface.co/utter-project/EuroFilter-v1). This shift helps the model refine its understanding across diverse languages and domains.
  4. + +
  5. Annealing to Zero (100 billion tokens) In this final stage, the learning rate decays linearly to zero. In this phase, the data mix was optimized to be of even higher quality, in order to polish the model's performance, and long context data sources were upsampled to increase the model context window to 32k tokens.
  6. +
+ +### Post-training + +This model was not post-trained. For an instruction-following version of this model see [EuroLLM-22B-Instruct-2515](https://huggingface.co/utter-project/EuroLLM-22B-Instruct-2512). + +## Run the model + + from transformers import AutoModelForCausalLM, AutoTokenizer + + model_id = "utter-project/EuroLLM-22B-2512" + tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id) + + text = "English: My name is EuroLLM. Portuguese:" + + inputs = tokenizer(text, return_tensors="pt") + outputs = model.generate(**inputs, max_new_tokens=20) + print(tokenizer.decode(outputs[0], skip_special_tokens=True)) + +## Bias, Risks, and Limitations + +EuroLLM-22B has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements). + +## Citation +If you use our work, please cite: +``` +@misc{ramos2026eurollm22btechnicalreport, + title={EuroLLM-22B: Technical Report}, + author={Miguel Moura Ramos and Duarte M. Alves and Hippolyte Gisserot-Boukhlef and João Alves and Pedro Henrique Martins and Patrick Fernandes and José Pombal and Nuno M. Guerreiro and Ricardo Rei and Nicolas Boizard and Amin Farajian and Mateusz Klimaszewski and José G. C. de Souza and Barry Haddow and François Yvon and Pierre Colombo and Alexandra Birch and André F. T. Martins}, + year={2026}, + eprint={2602.05879}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2602.05879}, +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..2cce4b6 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 6144, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 32768, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 48, + "num_hidden_layers": 54, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "tie_word_embeddings": false, + "transformers_version": "4.56.1", + "use_cache": true, + "vocab_size": 128000 +} 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..3a4736a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.56.1" +} diff --git a/model-00001-of-00010.safetensors b/model-00001-of-00010.safetensors new file mode 100644 index 0000000..a8956ce --- /dev/null +++ b/model-00001-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59397faa9d20234f4d91d14800a4b6e69bcf941d13e94072b0cdaa39ffccbc7 +size 4869690024 diff --git a/model-00002-of-00010.safetensors b/model-00002-of-00010.safetensors new file mode 100644 index 0000000..d6fc705 --- /dev/null +++ b/model-00002-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729436606840d90771b204bfe9205b8ef0e2e7a4c434aeace99c81d34d47b8b3 +size 4882323696 diff --git a/model-00003-of-00010.safetensors b/model-00003-of-00010.safetensors new file mode 100644 index 0000000..d4cffa6 --- /dev/null +++ b/model-00003-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d732e0f452e5754d1630d7545a9bd0ef012afff9b0b6d2bad0eb876a500e61a +size 4882323744 diff --git a/model-00004-of-00010.safetensors b/model-00004-of-00010.safetensors new file mode 100644 index 0000000..22f6ef6 --- /dev/null +++ b/model-00004-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db48e30ddd659c8e34f6fa83105d98b789b6df4619d3ee6c8c6f8644ec6ab45c +size 4983012192 diff --git a/model-00005-of-00010.safetensors b/model-00005-of-00010.safetensors new file mode 100644 index 0000000..af5129b --- /dev/null +++ b/model-00005-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b80785d14a3355316023a963a8e9288f5b8ee0ac93eb0df344ad910307761b +size 4957821336 diff --git a/model-00006-of-00010.safetensors b/model-00006-of-00010.safetensors new file mode 100644 index 0000000..cefdc4e --- /dev/null +++ b/model-00006-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba4a2e803bddc2d689628080df9d8da4264b82da7f3b5c08cc69a06b87b04a2 +size 4882323744 diff --git a/model-00007-of-00010.safetensors b/model-00007-of-00010.safetensors new file mode 100644 index 0000000..48aefdf --- /dev/null +++ b/model-00007-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd03c561fd327a3dcd56ed931a748f8aab9227a42c855015bea8bfe3eb62e975 +size 4983012192 diff --git a/model-00008-of-00010.safetensors b/model-00008-of-00010.safetensors new file mode 100644 index 0000000..270d0c7 --- /dev/null +++ b/model-00008-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3838c293a14aa31e59d30803606be22050e022d119e16d289bce84f3f2ad6e0 +size 4957821336 diff --git a/model-00009-of-00010.safetensors b/model-00009-of-00010.safetensors new file mode 100644 index 0000000..c5e82fc --- /dev/null +++ b/model-00009-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d16c17547019aa016aebc2312269d0ecd386c451902667222159616204b09f00 +size 4303521472 diff --git a/model-00010-of-00010.safetensors b/model-00010-of-00010.safetensors new file mode 100644 index 0000000..6f36cfb --- /dev/null +++ b/model-00010-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0c95d7676db91924fd5699f28c570278a8e548301830bf8d608cf03a5104d3 +size 1572864128 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..7a33d2d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,497 @@ +{ + "metadata": { + "total_parameters": 22637328384, + "total_size": 45274656768 + }, + "weight_map": { + "lm_head.weight": "model-00010-of-00010.safetensors", + "model.embed_tokens.weight": "model-00001-of-00010.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.27.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.28.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.30.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.31.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.32.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.33.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.34.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.35.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.36.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.37.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.38.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.39.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.40.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.41.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.42.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.43.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.44.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.45.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.46.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.47.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.48.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.49.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.50.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.51.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.52.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.53.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.norm.weight": "model-00009-of-00010.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..2d619c7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e4810e827e4ffcd735429d19d585326bb4efb31e921cb870ecefc4c1fa16e3 +size 15783507 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..062965b --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254 +size 2408875 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..646221b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2107 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "108": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "217": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "218": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "219": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "220": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "221": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "222": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "223": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "224": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "225": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "226": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "227": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "228": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "229": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "230": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "231": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "232": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "233": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "234": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "235": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "236": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "237": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "238": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "239": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "240": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "241": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "242": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "243": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "244": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "245": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "246": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "247": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "248": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "249": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "250": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "251": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "252": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "253": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "254": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "256": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "257": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "258": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "259": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "260": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}