commit 17eed69be1c85bb492a00b27815f1679fcb912ce Author: ModelHub XC Date: Wed May 27 16:12:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: upstage/SOLAR-10.7B-v1.0 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..292b681 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.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-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..d97c20d --- /dev/null +++ b/README.md @@ -0,0 +1,109 @@ +--- +license: apache-2.0 +--- + +

+ + + +

+ + +# **Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling!** + + +# **Introduction** +We introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B. + +We present a methodology for scaling LLMs called depth up-scaling (DUS) , which encompasses architectural modifications and continued pretraining. In other words, we integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model. + + +SOLAR-10.7B has remarkable performance. It outperforms models with up to 30B parameters, even surpassing the recent Mixtral 8X7B model. For detailed information, please refer to the experimental table. +Solar 10.7B is an ideal choice for fine-tuning. SOLAR-10.7B offers robustness and adaptability for your fine-tuning needs. Our simple instruction fine-tuning using the SOLAR-10.7B pre-trained model yields significant performance improvements ([SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)). + +For full details of this model please read our [paper](https://arxiv.org/abs/2312.15166). + +# **Evaluation Results** +| Model | H6 | Model Size | +|----------------------------------------|-------|------------| +| **SOLAR-10.7B-Instruct-v1.0** | **74.20** | **~ 11B** | +| mistralai/Mixtral-8x7B-Instruct-v0.1 | 72.62 | ~ 46.7B | +| 01-ai/Yi-34B-200K | 70.81 | ~ 34B | +| 01-ai/Yi-34B | 69.42 | ~ 34B | +| mistralai/Mixtral-8x7B-v0.1 | 68.42 | ~ 46.7B | +| meta-llama/Llama-2-70b-hf | 67.87 | ~ 70B | +| tiiuae/falcon-180B | 67.85 | ~ 180B | +| **SOLAR-10.7B-v1.0** | **66.04** | **~11B** | +| mistralai/Mistral-7B-Instruct-v0.2 | 65.71 | ~ 7B | +| Qwen/Qwen-14B | 65.86 | ~ 14B | +| 01-ai/Yi-34B-Chat | 65.32 | ~34B | +| meta-llama/Llama-2-70b-chat-hf | 62.4 | ~ 70B | +| mistralai/Mistral-7B-v0.1 | 60.97 | ~ 7B | +| mistralai/Mistral-7B-Instruct-v0.1 | 54.96 | ~ 7B | + +# **Usage Instructions** + +This model is pre-trained and is capable of just generating random text. To use it for chatting, you must fine-tune the model first. + +### **Version** + +Make sure you have the correct version of the transformers library installed: + +```sh +pip install transformers==4.35.2 +``` + +### **Loading the Model** + +Use the following Python code to load the model: + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +tokenizer = AutoTokenizer.from_pretrained("Upstage/SOLAR-10.7B-v1.0") +model = AutoModelForCausalLM.from_pretrained( + "Upstage/SOLAR-10.7B-v1.0", + device_map="auto", + torch_dtype=torch.float16, +) +``` + +### **Generating Text** + +To generate text, use the following Python code: + +```python +text = "Hi, my name is " +inputs = tokenizer(text, return_tensors="pt") + +outputs = model.generate(**inputs, max_new_tokens=64) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +### **License** +- [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0): apache-2.0 +- [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0): cc-by-nc-4.0 + - Since some non-commercial datasets such as Alpaca are used for fine-tuning, we release fine-tuned model as cc-by-nc-4.0. + +### **How to Cite** + +Please cite this model using this format. + +```bibtex +@misc{kim2023solar, + title={SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling}, + author={Dahyun Kim and Chanjun Park and Sanghoon Kim and Wonsung Lee and Wonho Song and Yunsu Kim and Hyeonwoo Kim and Yungi Kim and Hyeonju Lee and Jihoo Kim and Changbae Ahn and Seonghoon Yang and Sukyung Lee and Hyunbyung Park and Gyoungjin Gim and Mikyoung Cha and Hwalsuk Lee and Sunghun Kim}, + year={2023}, + eprint={2312.15166}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` + +### **The Upstage AI Team** ### +Upstage is creating the best LLM and DocAI. Please find more information at https://upstage.ai + +### **Contact Us** ### +Any questions and suggestions, please use the discussion tab. If you want to contact us directly, drop an email to [contact@upstage.ai ](mailto:contact@upstage.ai) + diff --git a/config.json b/config.json new file mode 100644 index 0000000..91f31d2 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "Upstage/SOLAR-10.7B-v1.0", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.35.2", + "use_cache": false, + "vocab_size": 32000 +} 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..75bff52 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.35.2", + "use_cache": false +} + diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..1820412 --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65340271224cbc1329c432b4ea8a2103cf1b31a329ba0a7ee91d47bfe5ab605d +size 4943162240 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..3fc3f20 --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e50d1c06fa5bda313bf0b8729e0ab431f8e6e3cbe9e0a82c4df48539a92bc7 +size 4999819232 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..2dd9005 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7f35be9cbf616f7fe9848d0622a6280b3d0589b2e1eade9d37e916dc43a8df +size 4915916080 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..fdc6d1d --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ef59f1f5029fc3e3fefabbf8cdf72bd3ef97f5f7fe2ca9b52d5a9a94682c05 +size 4915916080 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..3b283dd --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c70200d2bc7e658ce80f08f2de54e33961dba817e164c64f90dd14a25ab3d38 +size 1688284744 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d81a244 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,442 @@ +{ + "metadata": { + "total_size": 21463048192 + }, + "weight_map": { + "lm_head.weight": "model-00005-of-00005.safetensors", + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.norm.weight": "model-00005-of-00005.safetensors" + } +} diff --git a/solar_logo.png b/solar_logo.png new file mode 100644 index 0000000..2f63b13 Binary files /dev/null and b/solar_logo.png differ diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..a52c50a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,5 @@ +{ + "bos_token": "", + "eos_token": "", + "unk_token": "" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..61607de --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc +size 1795303 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0fe140a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "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 + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "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": true +}