commit 1af2af7eec2f88a68922c4bde08f0853534b9584 Author: ModelHub XC Date: Fri May 22 19:55:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: 01ai/Yi-Coder-9B-Chat Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b7e9e3a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3133c2 --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +license: apache-2.0 +--- +
+ + + + + +
+ +

+ 🐙 GitHub • + 👾 Discord • + 🐤 Twitter • + 💬 WeChat +
+ 📝 Paper • + 💪 Tech Blog • + 🙌 FAQ • + 📗 Learning Hub +

+ +# Intro + +Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters. + +Key features: +- Excelling in long-context understanding with a maximum context length of 128K tokens. +- Supporting 52 major programming languages: +```bash + 'java', 'markdown', 'python', 'php', 'javascript', 'c++', 'c#', 'c', 'typescript', 'html', 'go', 'java_server_pages', 'dart', 'objective-c', 'kotlin', 'tex', 'swift', 'ruby', 'sql', 'rust', 'css', 'yaml', 'matlab', 'lua', 'json', 'shell', 'visual_basic', 'scala', 'rmarkdown', 'pascal', 'fortran', 'haskell', 'assembly', 'perl', 'julia', 'cmake', 'groovy', 'ocaml', 'powershell', 'elixir', 'clojure', 'makefile', 'coffeescript', 'erlang', 'lisp', 'toml', 'batchfile', 'cobol', 'dockerfile', 'r', 'prolog', 'verilog' + ``` + +For model details and benchmarks, see [Yi-Coder blog](https://01-ai.github.io/) and [Yi-Coder README](https://github.com/01-ai/Yi-Coder). + +

+ demo1 +

+ +# Models + +| Name | Type | Length | Download | +|--------------------|------|----------------|---------------------------------------------------------------------------------------------------------------------------------------------------| +| Yi-Coder-9B-Chat | Chat | 128K | [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-9B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-9B-Chat) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-9B-Chat) | +| Yi-Coder-1.5B-Chat | Chat | 128K | [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-1.5B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-1.5B-Chat) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-1.5B-Chat) | +| Yi-Coder-9B | Base | 128K | [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-9B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-9B) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-9B) | +| Yi-Coder-1.5B | Base | 128K | [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-1.5B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-1.5B) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-1.5B) | +| | + +# Benchmarks + +As illustrated in the figure below, Yi-Coder-9B-Chat achieved an impressive 23% pass rate in LiveCodeBench, making it the only model with under 10B parameters to surpass 20%. It also outperforms DeepSeekCoder-33B-Ins at 22.3%, CodeGeex4-9B-all at 17.8%, CodeLLama-34B-Ins at 13.3%, and CodeQwen1.5-7B-Chat at 12%. + +

+ bench1 +

+ +# Quick Start + +You can use transformers to run inference with Yi-Coder models (both chat and base versions) as follows: +```python +from modelscope import AutoTokenizer, AutoModelForCausalLM +import torch + +device = "cuda" # the device to load the model onto +model_path = "01ai/Yi-Coder-9B-Chat" + +tokenizer = AutoTokenizer.from_pretrained(model_path) +model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto",torch_dtype=torch.bfloat16,).eval() + +prompt = "Write a quick sort algorithm." +messages = [ + {"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": prompt} +] +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) +model_inputs = tokenizer([text], return_tensors="pt").to(device) + +generated_ids = model.generate( + model_inputs.input_ids, + max_new_tokens=1024, + eos_token_id=tokenizer.eos_token_id +) +generated_ids = [ + output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) +] + +response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] +print(response) +``` + +For getting up and running with Yi-Coder series models quickly, see [Yi-Coder README](https://github.com/01-ai/Yi-Coder). + diff --git a/config.json b/config.json new file mode 100644 index 0000000..1bd3803 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 7, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 48, + "num_key_value_heads": 4, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.44.0", + "use_cache": false, + "vocab_size": 64000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..08b8831 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text2text-generation"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..bc9b471 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 7, + "pad_token_id": 0, + "transformers_version": "4.44.0" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..7b5977c --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4746e218b60b800840c62cef670c309489b832d3908a3605800c2769596601 +size 4932711424 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..ae90d44 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37ba7b04039ed5e9564d54c45cece5166ed7c86f75528567f019f9c2ab31ba9 +size 4976802816 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..fe6e06f --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03c62b8eaec0ec5478d9dfdfe6e5ca0424173d4a2dab647d8a0d6bd029e892f2 +size 4968397360 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..3a06956 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e5d5d075c8d582b50780b541e97ea625e192665fa7eeb211963fa421ff368d +size 2780953384 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..e03bed6 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,442 @@ +{ + "metadata": { + "total_size": 17658814464 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..0cc7f9d --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_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.model b/tokenizer.model new file mode 100644 index 0000000..8306c82 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39 +size 1033105 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9d5de42 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,61 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|startoftext|>", + "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "legacy": true, + "model_max_length": 200000, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}