commit a64472935428c6a246c65f3b13b604053d69411b Author: ModelHub XC Date: Mon Aug 31 10:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: CreitinGameplays/Mistral-Nemo-12B-R1-v0.4 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..85abb73 --- /dev/null +++ b/README.md @@ -0,0 +1,32 @@ +--- +base_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +license: apache-2.0 +language: +- en +datasets: +- allura-forge/doubao-seed2.0-claude-distill-v1-qwen3.5-format +--- + +# Uploaded finetuned model + +- **Developed by:** CreitinGameplays +- **License:** apache-2.0 +- **Finetuned from model :** unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit + +This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. + +[](https://github.com/unslothai/unsloth) + + + +Recommended generation parameters: +- Temperature: 0.6 - 0.9 +- Top_P = 0.95 +- Top_K = 40 +- Repeat Penalty = 1.0 (default) +- Do Sample = true \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..4d17c67 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ '[INST] ' + messages[0]['content'] + ' ' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ '\n' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n' }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..7e2e384 --- /dev/null +++ b/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "torch_dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": 10, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "unsloth_version": "2026.3.4", + "use_cache": false, + "vocab_size": 131072 +} \ No newline at end of file diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..58740e9 --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0ead7e365abc1d3ea5f109b3ed709cbf354b63f870dd8db3c7ce01336ec273 +size 4865522496 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..d691178 --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb80aeca83baf4a49a33fa92a2e01e9247955ae29ef66cb0c4d562454b1bfce +size 4907529424 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..af00f5f --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370924bd59231cf389a67be281e12ac977027610f88bf9476ea6c82e9705d4c5 +size 4907529456 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..ee2e607 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8a46780bc74c37fad1042ad01494bcf37733740913100a1d27055abcabf4af1 +size 4907529456 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..7d1add5 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0391db6107b18a08dbe6dda33386d5f4b7cd248e39a07a783576a95e2fb2a534 +size 4907496272 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..79fe50f --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,370 @@ +{ + "metadata": { + "total_size": 24495564800 + }, + "weight_map": { + "lm_head.weight": "model-00005-of-00005.safetensors", + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.norm.weight": "model-00005-of-00005.safetensors" + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..4e74d59 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2 +size 17078292 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..69f0d70 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,20 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "from_slow": true, + "is_local": true, + "legacy": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "", + "padding_side": "left", + "tokenizer_class": "TokenizersBackend", + "unk_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ '[INST] ' + messages[0]['content'] + ' ' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ '\\n' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\\n' }}{% endif %}" +} \ No newline at end of file