commit 7f398d4b66ac225d9e4a308ce33e07051a1e7f32 Author: ModelHub XC Date: Mon May 4 11:52:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Liangmingxin/ThetaWave-7B-sft Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9768943 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +license: apache-2.0 +datasets: +- Open-Orca/SlimOrca +pipeline_tag: text-generation +--- + +Obtained from freecs/ThetaWave-7B after SFT fine tuning. + +Open-Orca/SlimOrca datasets were used. + +The model does not currently support system_prompt because it uses mistral's chat_template, and the next release is in training to switch to the chatml template to support system_prompt. system_prompt can be implemented if you manually change the chat_template, but the After testing, this seems to degrade the model performance. + +More model details will be released... + +Vllm deployment command +``` +# Single graphics card +python /path/to/vllm/vllm/entrypoints/openai/api_server.py \ +--model '/path/to/ThetaWave-7B-sft' \ +--tokenizer '/path/to/ThetaWave-7B-sft' \ +--tokenizer-mode auto \ +--dtype float16 \ +--enforce-eager \ +--host 0.0.0.0 \ +--port 6000 \ +--disable-log-stats \ +--disable-log-requests + +# Dual graphics cards +python /path/to/vllm/vllm/entrypoints/openai/api_server.py \ +--model '/path/to/ThetaWave-7B-sft' \ +--tokenizer '/path/to/ThetaWave-7B-sft' \ +--tokenizer-mode auto \ +--dtype float16 \ +--enforce-eager \ +--tensor-parallel-size 2 \ +--worker-use-ray \ +--engine-use-ray \ +--host 0.0.0.0 \ +--port 6000 \ +--disable-log-stats \ +--disable-log-requests +``` + +Try it directly: +``` +from transformers import AutoModelForCausalLM, AutoTokenizer + +device = "cuda" # the device to load the model onto + +model = AutoModelForCausalLM.from_pretrained("Liangmingxin/ThetaWave-7B-sft") +tokenizer = AutoTokenizer.from_pretrained("Liangmingxin/ThetaWave-7B-sft") + +messages = [ + {"role": "user", "content": "Who are you?"}, +] + +encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") + +model_inputs = encodeds.to(device) +model.to(device) + +generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) +decoded = tokenizer.batch_decode(generated_ids) +print(decoded[0]) +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8c56f39 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "/home/myuser/ThetaWave-7B", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "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": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..5326931 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.37.0" +} diff --git a/model-00001-of-00008.safetensors b/model-00001-of-00008.safetensors new file mode 100644 index 0000000..d12a95f --- /dev/null +++ b/model-00001-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2462b88a0e7225f9f0b67a070cb82871b0bedd2bbdcae1e84d6637180affff4c +size 1889587040 diff --git a/model-00002-of-00008.safetensors b/model-00002-of-00008.safetensors new file mode 100644 index 0000000..e6eb060 --- /dev/null +++ b/model-00002-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeeb398a089eaa2d747317ba74ea7f2acd6c13f064156f71a4b325d2a7782deb +size 1946243936 diff --git a/model-00003-of-00008.safetensors b/model-00003-of-00008.safetensors new file mode 100644 index 0000000..9a8409d --- /dev/null +++ b/model-00003-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b27b7b9d985ce313dad7ea44be606802b3108a71c9465af25e4c715e6c3ee8c +size 1979781432 diff --git a/model-00004-of-00008.safetensors b/model-00004-of-00008.safetensors new file mode 100644 index 0000000..4d11ee2 --- /dev/null +++ b/model-00004-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a1cea3004b2a3c8d322155b553554969f0dcc5248d4fad3c543f6b8c349998 +size 1946243984 diff --git a/model-00005-of-00008.safetensors b/model-00005-of-00008.safetensors new file mode 100644 index 0000000..c55d044 --- /dev/null +++ b/model-00005-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396890f87a38509212df018d8484c73dfb8588ec7501f75291064ef304100985 +size 1979781448 diff --git a/model-00006-of-00008.safetensors b/model-00006-of-00008.safetensors new file mode 100644 index 0000000..aa80b25 --- /dev/null +++ b/model-00006-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc8f85514dfb51b7c244f12b317182b0214c6f23f1f86e88d835e3b0581f9a1 +size 1946243984 diff --git a/model-00007-of-00008.safetensors b/model-00007-of-00008.safetensors new file mode 100644 index 0000000..efda334 --- /dev/null +++ b/model-00007-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20bb5be241502234069b45d22a29059ae52f248654ebfd60fa95e4e6e30176ea +size 1979781448 diff --git a/model-00008-of-00008.safetensors b/model-00008-of-00008.safetensors new file mode 100644 index 0000000..6ea9076 --- /dev/null +++ b/model-00008-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e5764b5d7af51ba56cb9ba9309c3c09c178db1d4ef7b594e2c0ffe4813fa4a +size 815834680 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..fbc869b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00008-of-00008.safetensors", + "model.embed_tokens.weight": "model-00001-of-00008.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.norm.weight": "model-00008-of-00008.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.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..e88fefc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "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": "", + "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}