commit e5d21e684847bdb868f6eb39bea76b7ae71b3e08 Author: ModelHub XC Date: Sun May 31 12:22:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: louisbrulenaudet/Pearl-7B-slerp Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eded7db --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8a1988 --- /dev/null +++ b/README.md @@ -0,0 +1,142 @@ +--- +tags: +- merge +- mergekit +- Maths +- Mistral +base_model: +- mlabonne/OmniBeagle-7B +- WizardLM/WizardMath-7B-V1.1 +license: apache-2.0 +language: +- en +library_name: transformers +pipeline_tag: text-generation +model-index: + - name: Pearl-7B-slerp + results: + - task: + type: text-generation + metrics: + - name: Average + type: Average + value: 72.75 + - name: ARC + type: ARC + value: 68.00 + - name: GSM8K + type: GSM8K + value: 73.62 + - name: Winogrande + type: Winogrande + value: 68.00 + - name: TruthfulQA + type: TruthfulQA + value: 62.35 + - name: HellaSwag + type: HellaSwag + value: 87.16 + source: + name: Open LLM Leaderboard + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard +--- +
+ +# Pearl-7B-slerp, an xtraordinary 7B model for maths + +**03-22-2024 - To date, louisbrulenaudet/Pearl-34B-ties is the "Best 🤝 base merges and moerges model of around 30B" on the Open LLM Leaderboard.** + +Pearl-7B-slerp is a merge of the following models: +* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B) +* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1) + +### Evaluation + +The evaluation was performed using the HuggingFace Open LLM Leaderboard. + +| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | Params (B) | +|-------------------------------------------|------------|-------|-----------|-------|------------|------------|-------|--------------| +| **louisbrulenaudet/Pearl-7B-slerp** |**72.75** | 68.00 | 87.16 | 64.04 | 62.35 | 81.29 |**73.62**| 7.24 | +| mistralai/Mixtral-8x7B-Instruct-v0.1 | 72.62 | 70.22 | 87.63 | 71.16 | 64.58 | 81.37 | 60.73 | 46.7 | +| microsoft/phi-2 | 61.33 | 61.09 | 75.11 | 58.11 | 44.47 | 74.35 | 54.81 | 2.78 | +| microsoft/Orca-2-13b | 58.64 | 60.67 | 79.81 | 60.37 | 56.41 | 76.64 | 17.97 | 13 | +| mistralai/Mistral-7B-Instruct-v0.1 | 54.96 | 54.52 | 75.63 | 55.38 | 56.28 | 73.72 | 14.25 | 7.24 | +| meta-llama/Llama-2-7b-hf | 50.97 | 53.07 | 78.59 | 46.87 | 38.76 | 74.03 | 14.48 | 6.74 | + +Spherical Linear Interpolation (SLERP) serves as a technique for seamlessly interpolating between two vectors while maintaining a constant rate of change and upholding the geometric properties of the spherical space in which these vectors exist. + +Opting for SLERP over traditional linear interpolation is motivated by various considerations. Linear interpolation in high-dimensional spaces may result in a reduction in the magnitude of the interpolated vector, diminishing the scale of weights. Additionally, in many cases, the alteration in the weights' direction conveys more meaningful information, such as feature learning and representation, compared to the magnitude of change. + +$$ {\displaystyle \operatorname {slerp} (p_{0},p_{1};t)={\frac {\sin {[(1-t)\Omega }]}{\sin \Omega }}p_{0}+{\frac {\sin[t\Omega ]}{\sin \Omega }}p_{1}.}$$ + +The implementation of SLERP involves the following steps: +- Normalize the input vectors to unit length, ensuring they signify directions rather than magnitudes. +- Calculate the angle between these vectors using their dot product. +- If the vectors are nearly collinear, the method defaults to linear interpolation for efficiency. Otherwise, SLERP calculates scale factors based on the interpolation factor t (where t=0 corresponds to 100% of the first vector, and t=1 corresponds to 100% of the second vector) and the angle between the vectors. +- Utilize these computed factors to weigh the original vectors, and then sum them to derive the interpolated vector. + +In essence, SLERP provides a robust mechanism for interpolating vectors, offering advantages in preserving directional information and mitigating issues associated with linear interpolation in high-dimensional spaces. + + +## Configuration + +```yaml +slices: + - sources: + - model: mlabonne/OmniBeagle-7B + layer_range: [0, 32] + - model: WizardLM/WizardMath-7B-V1.1 + layer_range: [0, 32] +merge_method: slerp +base_model: mlabonne/OmniBeagle-7B +parameters: + t: + - filter: self_attn + value: [0, 0.5, 0.3, 0.7, 1] + - filter: mlp + value: [1, 0.5, 0.7, 0.3, 0] + - value: 0.5 +dtype: bfloat16 +``` + +## Usage + +```python +!pip install -qU transformers accelerate + +from transformers import AutoTokenizer +import transformers +import torch + +model = "louisbrulenaudet/Pearl-7B-slerp" +messages = [{"role": "user", "content": "What is a large language model?"}] + +tokenizer = AutoTokenizer.from_pretrained(model) +prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +pipeline = transformers.pipeline( + "text-generation", + model=model, + torch_dtype=torch.float16, + device_map="auto", +) + +outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) +print(outputs[0]["generated_text"]) +``` + +## Citing & Authors + +If you use this code in your research, please use the following BibTeX entry. + +```BibTeX +@misc{louisbrulenaudet2023, + author = {Louis Brulé Naudet}, + title = {Pearl-7B-slerp, an xtraordinary 7B model for maths}, + year = {2023} + howpublished = {\url{https://huggingface.co/louisbrulenaudet/Pearl-7B-slerp}}, +} +``` + +## Feedback + +If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com). \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..fbe14e8 --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "mlabonne/OmniBeagle-7B", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.35.2", + "use_cache": true, + "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/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..91ddf96 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,17 @@ + +slices: + - sources: + - model: mlabonne/OmniBeagle-7B + layer_range: [0, 32] + - model: WizardLM/WizardMath-7B-V1.1 + layer_range: [0, 32] +merge_method: slerp +base_model: mlabonne/OmniBeagle-7B +parameters: + t: + - filter: self_attn + value: [0, 0.5, 0.3, 0.7, 1] + - filter: mlp + value: [1, 0.5, 0.7, 0.3, 0] + - value: 0.5 +dtype: bfloat16 diff --git a/model-00001-of-00008.safetensors b/model-00001-of-00008.safetensors new file mode 100644 index 0000000..f06f22b --- /dev/null +++ b/model-00001-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7de0e3b841f1a7dc5094086cb4aff27c227a0a94b8a36b4fb074b65b6294a3 +size 1912681584 diff --git a/model-00002-of-00008.safetensors b/model-00002-of-00008.safetensors new file mode 100644 index 0000000..9c4ddd9 --- /dev/null +++ b/model-00002-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c3a1ab45b2f3872b49f5707d4005c0ebdf95147fe4335ddaa8634c55ce51711 +size 1979781456 diff --git a/model-00003-of-00008.safetensors b/model-00003-of-00008.safetensors new file mode 100644 index 0000000..a9fb189 --- /dev/null +++ b/model-00003-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff34561db95ab77f54309734fdbcad73cef54d7dc82c63124464460f47709db4 +size 1946243968 diff --git a/model-00004-of-00008.safetensors b/model-00004-of-00008.safetensors new file mode 100644 index 0000000..61727e0 --- /dev/null +++ b/model-00004-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc1440d8325fb7efedbf3ebe85c30d6b299ee67bc50e28850cc2f9704e38c41 +size 1979781416 diff --git a/model-00005-of-00008.safetensors b/model-00005-of-00008.safetensors new file mode 100644 index 0000000..c11760f --- /dev/null +++ b/model-00005-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874a2392c16eef3cd55ef9786dadc7f256ab504ee8d48b7183e00c7629106504 +size 1862349080 diff --git a/model-00006-of-00008.safetensors b/model-00006-of-00008.safetensors new file mode 100644 index 0000000..e8916ac --- /dev/null +++ b/model-00006-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4782c99c7ddc5d3fa78a4a68648226ac13f1a926fcb227f70b3963372c7d82f3 +size 1916866512 diff --git a/model-00007-of-00008.safetensors b/model-00007-of-00008.safetensors new file mode 100644 index 0000000..c1a7651 --- /dev/null +++ b/model-00007-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab362fbe94d94a9c40dedf6411290a381dc22d38c199e283cb1d252cf2d1bee6 +size 1979781456 diff --git a/model-00008-of-00008.safetensors b/model-00008-of-00008.safetensors new file mode 100644 index 0000000..1898b13 --- /dev/null +++ b/model-00008-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b08baf485bdef3ff9a7255250b10cb5459193e0872a18dbac91bc7253f5902 +size 906012472 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..4faef89 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.embed_tokens.weight": "model-00006-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.norm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors"}} \ No newline at end of file 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..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..0f5e094 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,40 @@ +{ + "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": false +}