commit 947b5c7c8518d01aebb482cc987b94876ce0e2ac Author: ModelHub XC Date: Wed Aug 5 22:57:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Sorihon/Extraordinary-Journey-24B 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..49e8863 --- /dev/null +++ b/README.md @@ -0,0 +1,26 @@ +--- +base_model: + - Sorihon/Royal-Realms-24B + - LatitudeGames/Hearthfire-24B + - Gryphe/Codex-24B-Small-3.2 + - ReadyArt/Dark-Nexus-24B-v2.0 + - Delta-Vector/Rei-24B-KTO + - Entropicengine/Pinecone-sage-24b + - CrucibleLab/M3.2-24B-Loki-V1.3 +library_name: transformers +tags: +- mergekit +- merge + +--- +### Models Merged +The following models were included in the merge: + - CrucibleLab/M3.2-24B-Loki-V1.3 + - Delta-Vector/Rei-24B-KTO + - Entropicengine/Pinecone-sage-24b + - Gryphe/Codex-24B-Small-3.2 + - LatitudeGames/Hearthfire-24B + - ReadyArt/Dark-Nexus-24B-v2.0 + - Sorihon/Royal-Realms-24B + + diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..25195da --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + ' +' + message['content'] + '<|im_end|>' + ' +'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant +' }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..72ca7fd --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 999, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 32768, + "max_position_embeddings": 131072, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 1000000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.9.0", + "use_cache": false, + "vocab_size": 131074 +} diff --git a/model-00001-of-00010.safetensors b/model-00001-of-00010.safetensors new file mode 100644 index 0000000..fad8f84 --- /dev/null +++ b/model-00001-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0198bc1c92ce4c336b5953daa9af7f4685c328cf5539ddd5dd56526adebff4cf +size 4907430272 diff --git a/model-00002-of-00010.safetensors b/model-00002-of-00010.safetensors new file mode 100644 index 0000000..4f5ae19 --- /dev/null +++ b/model-00002-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23102ebcc47f450ddaa5ad203f02e167df0acf2ff45fb1a5650956bd6fee88c5 +size 4781592832 diff --git a/model-00003-of-00010.safetensors b/model-00003-of-00010.safetensors new file mode 100644 index 0000000..39d5c0e --- /dev/null +++ b/model-00003-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a18be2457faacc900a44aba6c1f9d4dd45ac00b7c6425cb54006f184b23e225 +size 4781592816 diff --git a/model-00004-of-00010.safetensors b/model-00004-of-00010.safetensors new file mode 100644 index 0000000..266d88d --- /dev/null +++ b/model-00004-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e818dbc24603c9b3e9082e2a6464946fe2476171e7be6c3e05ff838b02917a81 +size 4886471592 diff --git a/model-00005-of-00010.safetensors b/model-00005-of-00010.safetensors new file mode 100644 index 0000000..0b2062a --- /dev/null +++ b/model-00005-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c295a97b1752dea4a17e0f99270487d999452703cf45c480199c3b24574ea5 +size 4781592832 diff --git a/model-00006-of-00010.safetensors b/model-00006-of-00010.safetensors new file mode 100644 index 0000000..9cd2cf1 --- /dev/null +++ b/model-00006-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70277f7ed2a9e4772aab3231e0a30585c7d51f89befc1efc3228ad69e8fff25e +size 4781592816 diff --git a/model-00007-of-00010.safetensors b/model-00007-of-00010.safetensors new file mode 100644 index 0000000..a043bf7 --- /dev/null +++ b/model-00007-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14503da8d633ea2fc9268361789476d3af23a033235721d0778abb945257eded +size 4886471592 diff --git a/model-00008-of-00010.safetensors b/model-00008-of-00010.safetensors new file mode 100644 index 0000000..c555352 --- /dev/null +++ b/model-00008-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9c3dbcff12edd192adfce5a8723ed7e621ae64f24ee87f4dd7a78ce3941209 +size 4781592832 diff --git a/model-00009-of-00010.safetensors b/model-00009-of-00010.safetensors new file mode 100644 index 0000000..bc4a306 --- /dev/null +++ b/model-00009-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7199c38e57b9d49c5c23e4a8d51c4eb1fbd660dbe4962a29267e7c8d083c7ac6 +size 4781592800 diff --git a/model-00010-of-00010.safetensors b/model-00010-of-00010.safetensors new file mode 100644 index 0000000..43cdfcf --- /dev/null +++ b/model-00010-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd33d2301cd025e64b2d9748b39b40468a834888f6c00979a865292d07ea861 +size 3774959456 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..3846d9c --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,371 @@ +{ + "metadata": { + "total_size": 47144847360, + "mergekit_version": "0.1.4" + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00010.safetensors", + "model.embed_tokens.weight": "model-00001-of-00010.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", + "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", + "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", + "model.norm.weight": "model-00010-of-00010.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..99210c6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405d32ddfe14414696d296b2de2b84cb40fc3c8c5665816d7bf4e77268ad9093 +size 17078409 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..1c18bc9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": null, + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "is_local": true, + "legacy": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "", + "tokenizer_class": "TokenizersBackend", + "unk_token": "", + "use_default_system_prompt": false +}