commit 62daa9726aba5705e6fe378c86a619fbd4f65b68 Author: ModelHub XC Date: Thu Sep 24 07:16:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: pszemraj/perSLIMmon-8b-base Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8702ec3 --- /dev/null +++ b/README.md @@ -0,0 +1,62 @@ +--- +license: apache-2.0 +language: +- en +pipeline_tag: text-generation +tags: +- persimmon +--- + +# perSLIMmon-8b-base + +> persimmon-8b went to the vocab lipo clinic + + +A slimmed-down version of [persimmon-8b-base](https://huggingface.co/adept/persimmon-8b-base) which removes the ~70,000 unused entries in the model vocabulary and tokenizer (see the safetensors layer overview). Should be _slightly_ faster. + +Credit: [fine-tune-fuyu](https://github.com/phillip-kravtsov/fine-tune-fuyu) (`scripts/surgery.py` was adapted for persimmon) + + +## inference + +install required pkgs: + +```sh +pip install -U transformers accelerate bitsandbytes sentencepiece +``` + +load in 4bit & run inference: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +tokenizer = AutoTokenizer.from_pretrained("pszemraj/perSLIMmon-8b-base") +model = AutoModelForCausalLM.from_pretrained( + "pszemraj/perSLIMmon-8b-base", + load_in_4bit=True, # GPU required + torch_dtype="auto", + device_map="auto", +) +inputs = tokenizer("The weather is always wonderful", return_tensors="pt").to( + model.device +) +tokens = model.generate( + **inputs, + max_new_tokens=64, + temperature=0.75, + top_p=0.95, + epsilon_cutoff=1e-5, + repetition_penalty=1.05, + renormalize_logits=True, + do_sample=True, +) # adapt inference params as needed + +print(tokenizer.decode(tokens[0], skip_special_tokens=True)) +``` + +inference is decently fast on a colab T4: + +``` +CPU times: user 6.01 s, sys: 138 ms, total: 6.15 s +Wall time: 6.23 s +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..6c88dc1 --- /dev/null +++ b/config.json @@ -0,0 +1,31 @@ +{ + "_name_or_path": "/content/perSLIMmon-8b", + "architectures": [ + "PersimmonForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 71013, + "eos_token_id": 71013, + "hidden_act": "relu2", + "hidden_dropout": 0.6, + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 16384, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 16384, + "model_type": "persimmon", + "num_attention_heads": 64, + "num_hidden_layers": 36, + "num_key_value_heads": 64, + "partial_rotary_factor": 0.5, + "pretraining_tp": 1, + "qk_layernorm": true, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 25000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 192144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b7734b2 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 71013, + "eos_token_id": 71013, + "transformers_version": "4.36.0.dev0" +} diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..b044d46 --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50fff7fa0e7f51815cb2d5f6467dc70c9175f740d896e7ff8ee140099a212b24 +size 2916581840 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..7b0f14f --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f440776aac976a0926a44acc9a3ea34c05e866ba81de81a9adcf71d1384e3b3 +size 2953584960 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..9c299de --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e440a26d5353562206366417e606eb6853c7b070698b65c299ec8b4b6a34bc +size 2953593696 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..b80caf8 --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be86179337428f6484657a47c08509c7d3a473a50ff2b0e96bd55c276bab070e +size 2953586264 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..781743c --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39304df5ebf640729a03ee690beb1dd20eb9bced39fff8d4898b06f95d3b642a +size 2953585048 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..b9ad55a --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c86e0bdbd2d093e45e180880109fbbe9cd8e569722832942155c662ba4708405 +size 2916605912 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..797d84b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,587 @@ +{ + "metadata": { + "total_size": 17647470592 + }, + "weight_map": { + "lm_head.weight": "model-00006-of-00006.safetensors", + "model.embed_tokens.weight": "model-00001-of-00006.safetensors", + "model.final_layernorm.bias": "model-00006-of-00006.safetensors", + "model.final_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.0.input_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.dense.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.dense.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.query_key_value.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.query_key_value.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.dense.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.dense.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.query_key_value.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.query_key_value.weight": "model-00001-of-00006.safetensors", + "model.layers.10.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.dense.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.dense.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.k_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.k_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.query_key_value.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.query_key_value.weight": "model-00002-of-00006.safetensors", + "model.layers.11.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.dense.bias": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.dense.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.k_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.k_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.q_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.q_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.query_key_value.bias": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.query_key_value.weight": "model-00003-of-00006.safetensors", + "model.layers.12.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.dense.bias": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.dense.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.k_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.k_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.q_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.q_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.query_key_value.bias": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.query_key_value.weight": "model-00003-of-00006.safetensors", + "model.layers.13.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.13.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.13.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors", + "model.layers.13.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.dense.bias": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.dense.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.k_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.k_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.q_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.q_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.query_key_value.bias": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.query_key_value.weight": "model-00003-of-00006.safetensors", + "model.layers.14.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.14.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.14.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors", + "model.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.dense.bias": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.dense.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.k_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.k_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.q_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.q_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.query_key_value.bias": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.query_key_value.weight": "model-00003-of-00006.safetensors", + "model.layers.15.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.dense.bias": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.dense.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.k_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.k_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.q_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.q_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.query_key_value.bias": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.query_key_value.weight": "model-00003-of-00006.safetensors", + "model.layers.16.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.dense.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.dense.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.k_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.k_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.query_key_value.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.query_key_value.weight": "model-00003-of-00006.safetensors", + "model.layers.17.input_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.dense.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.dense.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.q_layernorm.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.q_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.query_key_value.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.query_key_value.weight": "model-00003-of-00006.safetensors", + "model.layers.18.input_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.19.input_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.19.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors", + "model.layers.19.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors", + "model.layers.19.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors", + "model.layers.19.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.2.input_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.dense.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.dense.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.query_key_value.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.query_key_value.weight": "model-00001-of-00006.safetensors", + "model.layers.20.input_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.20.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors", + "model.layers.20.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors", + "model.layers.20.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors", + "model.layers.20.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.21.input_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.21.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors", + "model.layers.21.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors", + "model.layers.21.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors", + "model.layers.21.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.22.input_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.22.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors", + "model.layers.22.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors", + "model.layers.22.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors", + "model.layers.22.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.23.input_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.24.input_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.25.input_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.25.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors", + "model.layers.25.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors", + "model.layers.25.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.25.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.dense.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.dense.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.k_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.k_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.q_layernorm.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.q_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.query_key_value.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.query_key_value.weight": "model-00004-of-00006.safetensors", + "model.layers.26.input_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.dense.bias": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.dense.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.k_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.k_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.q_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.q_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.query_key_value.bias": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.query_key_value.weight": "model-00005-of-00006.safetensors", + "model.layers.27.input_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.27.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors", + "model.layers.27.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors", + "model.layers.27.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.27.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.dense.bias": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.dense.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.k_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.k_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.q_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.q_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.query_key_value.bias": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.query_key_value.weight": "model-00005-of-00006.safetensors", + "model.layers.28.input_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.28.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors", + "model.layers.28.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors", + "model.layers.28.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.28.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.28.post_attention_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.dense.bias": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.dense.weight": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.k_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.k_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.q_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.q_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.query_key_value.bias": "model-00005-of-00006.safetensors", + "model.layers.28.self_attn.query_key_value.weight": "model-00005-of-00006.safetensors", + "model.layers.29.input_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.29.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors", + "model.layers.29.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors", + "model.layers.29.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.29.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.29.post_attention_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.dense.bias": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.dense.weight": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.k_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.k_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.q_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.q_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.query_key_value.bias": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.query_key_value.weight": "model-00005-of-00006.safetensors", + "model.layers.3.input_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.3.self_attn.dense.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.dense.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_layernorm.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.query_key_value.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.query_key_value.weight": "model-00001-of-00006.safetensors", + "model.layers.30.input_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.30.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors", + "model.layers.30.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors", + "model.layers.30.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.30.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.30.post_attention_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.dense.bias": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.dense.weight": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.k_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.k_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.q_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.q_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.query_key_value.bias": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.query_key_value.weight": "model-00005-of-00006.safetensors", + "model.layers.31.input_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.31.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors", + "model.layers.31.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors", + "model.layers.31.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.31.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.31.post_attention_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.dense.bias": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.dense.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.k_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.k_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.q_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.q_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.query_key_value.bias": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.query_key_value.weight": "model-00005-of-00006.safetensors", + "model.layers.32.input_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.32.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.32.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors", + "model.layers.32.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors", + "model.layers.32.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors", + "model.layers.32.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors", + "model.layers.32.post_attention_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.32.self_attn.dense.bias": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.dense.weight": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.k_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.k_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.q_layernorm.bias": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.q_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.query_key_value.bias": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.query_key_value.weight": "model-00005-of-00006.safetensors", + "model.layers.33.input_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.33.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.33.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors", + "model.layers.33.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors", + "model.layers.33.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors", + "model.layers.33.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors", + "model.layers.33.post_attention_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.dense.bias": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.dense.weight": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.k_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.k_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.q_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.q_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.query_key_value.bias": "model-00006-of-00006.safetensors", + "model.layers.33.self_attn.query_key_value.weight": "model-00006-of-00006.safetensors", + "model.layers.34.input_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.34.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.34.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors", + "model.layers.34.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors", + "model.layers.34.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors", + "model.layers.34.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors", + "model.layers.34.post_attention_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.dense.bias": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.dense.weight": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.k_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.k_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.q_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.q_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.query_key_value.bias": "model-00006-of-00006.safetensors", + "model.layers.34.self_attn.query_key_value.weight": "model-00006-of-00006.safetensors", + "model.layers.35.input_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.35.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors", + "model.layers.35.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors", + "model.layers.35.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors", + "model.layers.35.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors", + "model.layers.35.post_attention_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.dense.bias": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.dense.weight": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.k_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.k_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.q_layernorm.bias": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.q_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.query_key_value.bias": "model-00006-of-00006.safetensors", + "model.layers.35.self_attn.query_key_value.weight": "model-00006-of-00006.safetensors", + "model.layers.4.input_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.dense.bias": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.dense.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.k_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.k_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.q_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.q_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.query_key_value.bias": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.query_key_value.weight": "model-00002-of-00006.safetensors", + "model.layers.5.input_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.dense.bias": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.dense.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.k_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.k_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.q_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.q_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.query_key_value.bias": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.query_key_value.weight": "model-00002-of-00006.safetensors", + "model.layers.6.input_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.dense.bias": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.dense.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.q_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.q_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.query_key_value.bias": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.query_key_value.weight": "model-00002-of-00006.safetensors", + "model.layers.7.input_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.dense.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.dense.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.query_key_value.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.query_key_value.weight": "model-00002-of-00006.safetensors", + "model.layers.8.input_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.dense.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.dense.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.query_key_value.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.query_key_value.weight": "model-00002-of-00006.safetensors", + "model.layers.9.input_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.dense.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.dense.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_layernorm.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.query_key_value.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.query_key_value.weight": "model-00002-of-00006.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..f3ea859 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,27 @@ +{ + "additional_special_tokens": [ + "", + "|ENDOFTEXT|" + ], + "bos_token": { + "content": "|ENDOFTEXT|", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "|ENDOFTEXT|", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e5d7879 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eff2fc809f3487daf5f26fbe36e3db3e538570b1e5f54b3581650274fd633b7 +size 12884565 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c556d0b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1013": { + "content": "|ENDOFTEXT|", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "|ENDOFTEXT|", + "clean_up_tokenization_spaces": false, + "eos_token": "|ENDOFTEXT|", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}