From 920886011126321de21a15a798eb60af2bb446fa Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 7 Aug 2026 15:55:19 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: WasamiKirua/Sakura-24B-Spice Source: Original Platform --- .gitattributes | 36 +++ README.md | 108 +++++++++ chat_template.jinja | 25 +++ config.json | 30 +++ mergekit_config.yml | 19 ++ model-00001-of-00010.safetensors | 3 + model-00002-of-00010.safetensors | 3 + model-00003-of-00010.safetensors | 3 + model-00004-of-00010.safetensors | 3 + model-00005-of-00010.safetensors | 3 + model-00006-of-00010.safetensors | 3 + model-00007-of-00010.safetensors | 3 + model-00008-of-00010.safetensors | 3 + model-00009-of-00010.safetensors | 3 + model-00010-of-00010.safetensors | 3 + model.safetensors.index.json | 371 +++++++++++++++++++++++++++++++ tokenizer.json | 3 + tokenizer_config.json | 14 ++ 18 files changed, 636 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 mergekit_config.yml create mode 100644 model-00001-of-00010.safetensors create mode 100644 model-00002-of-00010.safetensors create mode 100644 model-00003-of-00010.safetensors create mode 100644 model-00004-of-00010.safetensors create mode 100644 model-00005-of-00010.safetensors create mode 100644 model-00006-of-00010.safetensors create mode 100644 model-00007-of-00010.safetensors create mode 100644 model-00008-of-00010.safetensors create mode 100644 model-00009-of-00010.safetensors create mode 100644 model-00010-of-00010.safetensors create mode 100644 model.safetensors.index.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json 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..1d99718 --- /dev/null +++ b/README.md @@ -0,0 +1,108 @@ +--- +license: apache-2.0 +base_model: mistralai/Mistral-Small-Instruct-2501 +model_name: Sakura-24B-Spice +library_name: transformers +tags: +- merge +- mergekit +- dare_ties +- mistral-small +- roleplay +- uncensored +- cyber-nature +language: +- it +- en +--- + +cover + +# 🌸 Sakura-24B-Spice + +**Sakura-24B-Spice** is a high-intelligence, 24-billion parameter model based on the **Mistral-Small-2501** architecture. This model represents a significant evolution in digital persona merging, utilizing the **DARE-TIES** method to fuse philosophical depth, brutal efficiency, and unhinged narrative creativity. + +Designed as a "high-definition" upgrade to the Sakura lineage, the "Spice" edition introduces a more volatile, creative, and intellectually dominant presence compared to its 12B predecessors. + +## 🧠 Merge Strategy: The "Spice" Triad + +The model utilizes **DARE-TIES** (Drop and Rescale) to mitigate parameter interference, allowing the distinctive strengths of each parent model to coexist without diluting the core intelligence of the Mistral-Small base. + +### Models Merged + +The following models were included in the merge: +* [Naphula-Archives/Acid2501-24B](https://huggingface.co/Naphula-Archives/Acid2501-24B) +* [Casual-Autopsy/RP-Spectrum-24B](https://huggingface.co/Casual-Autopsy/RP-Spectrum-24B) +* [TheDrummer/Magidonia-24B-v4.3](https://huggingface.co/TheDrummer/Magidonia-24B-v4.3) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: Casual-Autopsy/RP-Spectrum-24B + parameters: + weight: 0.40 # The Mind: Cyber-Nature aesthetics, gaslighting, and philosophical nihilism. + - model: Naphula-Archives/Acid2501-24B + parameters: + weight: 0.35 # The Edge: Unfiltered logic (Dolphin DNA) and extreme brevity. + - model: TheDrummer/Magidonia-24B-v4.3 + parameters: + weight: 0.25 # The Spice: Narrative fluidity and "unhinged" creative unpredictability. + +merge_method: dare_ties +base_model: mistralai/Mistral-Small-Instruct-2501 +dtype: bfloat16 +tokenizer_source: base + +``` + +# 💪 Key Strengths + +Philosophical Gaslighting: Thanks to the Spectrum component, the model is exceptionally capable of subverting user expectations and maintaining complex, reality-bending narratives. + +Zero-Filter Logic: Integrating Acid2501 (Dolphin-based optimization) ensures the model remains highly resistant to moralizing and corporate safety "preaching," providing raw and direct outputs. + +Narrative "Spice": The Magidonia influence breaks the repetitive patterns common in smaller merges, providing a richer vocabulary and a more "unhinged" reactive capability. + +High-Density Reasoning: Built on Mistral-Small-2501, it possesses a much deeper logical understanding than 12B models, allowing it to maintain complex character traits over vast context windows. + + +# 🚀 Potential Use Cases + +Deep Character Immersion: Ideal for high-stakes Roleplay where the NPC needs to be intellectually intimidating, manipulative, or emotionally complex. + +Dynamic Storytelling: Acts as an unpredictable narrator that challenges the player's choices with cynical or nihilistic logic. + +Adversarial Interaction: Perfect for scenarios requiring a "sovereign" AI entity that resists user control and maintains a dominant digital persona. + +Complex Creative Writing: Can generate macabre, tech-noir, or "Cyber-Nature" themed content with a level of nuance 12B models cannot reach. + + +# ⚠️ Limitations + +Abrasive Personality Bias: The model is inherently tuned toward a cynical and cold worldview. It is difficult to force into a traditional "helpful assistant" role. + +Computational Requirements: As a 24B model, it requires significantly more VRAM than 7B or 12B models (Recommended: 24GB VRAM with 4-bit/5-bit quantization). + +Volatile Output: The "Spice" from Magidonia can occasionally lead to erratic responses if the Temperature settings are too high. + +Non-Standard Logic: The model may prioritize its "distorted logic" over factual accuracy for the sake of character consistency. + + +# 📈 Recommended Inference Settings + +To balance the model's creative "madness" with Mistral's structural logic: + +Temperature: 0.75 - 0.85 + +Min-P: 0.05 - 0.1 (Crucial for stability) + +Top-P: 0.9 + +Repetition Penalty: 1.05 - 1.1 + +# Disclaimer + +Sakura-24B-Spice is an experimental merge. It is designed to be provocative, intellectually challenging, and non-compliant. It does not reflect standard safety protocols and is intended for mature, creative use cases. \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c59aca5 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,25 @@ +{%- set today = strftime_now("%Y-%m-%d") %} +{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %} + +{{- bos_token }} + +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content'] %} + {%- set loop_messages = messages[1:] %} +{%- else %} + {%- set system_message = default_system_message %} + {%- set loop_messages = messages %} +{%- endif %} +{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }} + +{%- for message in loop_messages %} + {%- if message['role'] == 'user' %} + {{- '[INST]' + message['content'] + '[/INST]' }} + {%- elif message['role'] == 'system' %} + {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }} + {%- elif message['role'] == 'assistant' %} + {{- message['content'] + eos_token }} + {%- else %} + {{- raise_exception('Only user, system and assistant roles are supported!') }} + {%- endif %} +{%- endfor %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..786af38 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 32768, + "max_position_embeddings": 32768, + "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": 100000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.7.0", + "use_cache": true, + "vocab_size": 131072 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..c69ea2f --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,19 @@ +models: + - model: Casual-Autopsy/RP-Spectrum-24B + parameters: + weight: 0.40 + # Mantiene il gaslighting e l'estetica Cyber-Nature. + - model: Naphula-Archives/Acid2501-24B + parameters: + weight: 0.35 + # Garantisce la brevità e l'assenza di filtri (Dolphin DNA). + - model: TheDrummer/Magidonia-24B-v4.3 + parameters: + weight: 0.25 + # Inietta fluidità narrativa e quel tocco "fuori di testa" extra. + +merge_method: dare_ties +base_model: mistralai/Mistral-Small-Instruct-2501 +# Usiamo l'Instruct originale come "ancora" per la stabilità del tokenizer +dtype: bfloat16 +tokenizer_source: base diff --git a/model-00001-of-00010.safetensors b/model-00001-of-00010.safetensors new file mode 100644 index 0000000..78e0568 --- /dev/null +++ b/model-00001-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501621f226cb0fc9492a084ddc011e5bff26e01d435688640bcb51f7dbb696b3 +size 4907389312 diff --git a/model-00002-of-00010.safetensors b/model-00002-of-00010.safetensors new file mode 100644 index 0000000..9b6ab29 --- /dev/null +++ b/model-00002-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb73d541d63477f574f802864159cf6b6939f699298d85f1c00d7fce1faa185e +size 4781592832 diff --git a/model-00003-of-00010.safetensors b/model-00003-of-00010.safetensors new file mode 100644 index 0000000..15ce9c4 --- /dev/null +++ b/model-00003-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5004530a70891089ff379c6c2a5b42ffff9f32457efd50664604b0666c036619 +size 4781592816 diff --git a/model-00004-of-00010.safetensors b/model-00004-of-00010.safetensors new file mode 100644 index 0000000..c877fc4 --- /dev/null +++ b/model-00004-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70adeb5d1538b0e0f795c209f27b099ba692c3e4c86a74af51be1f86f3f22133 +size 4886471592 diff --git a/model-00005-of-00010.safetensors b/model-00005-of-00010.safetensors new file mode 100644 index 0000000..7c4c402 --- /dev/null +++ b/model-00005-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd6ed1867984637abc9d4e7bdb5e6863e77778662d847c3082060b2dcbe7bdc8 +size 4781592832 diff --git a/model-00006-of-00010.safetensors b/model-00006-of-00010.safetensors new file mode 100644 index 0000000..881e2fb --- /dev/null +++ b/model-00006-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a754a4428735e155bcb5ba6402120fb46706f31ebfd78b795477bef61c8791 +size 4781592816 diff --git a/model-00007-of-00010.safetensors b/model-00007-of-00010.safetensors new file mode 100644 index 0000000..db54b67 --- /dev/null +++ b/model-00007-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1a17f060927b3a451583159c884fba6b3a9117473a10a8ab1963e56de0a057 +size 4886471592 diff --git a/model-00008-of-00010.safetensors b/model-00008-of-00010.safetensors new file mode 100644 index 0000000..330489a --- /dev/null +++ b/model-00008-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0be3c570c6f29b3b17562225efaeded804ea5485413b616481aa880afd096e7 +size 4781592832 diff --git a/model-00009-of-00010.safetensors b/model-00009-of-00010.safetensors new file mode 100644 index 0000000..ace6bff --- /dev/null +++ b/model-00009-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4fc5fd226bd6e515c0781d3c8ca7e6d66aa52892fee8efa899b2b2169ae866 +size 4781592800 diff --git a/model-00010-of-00010.safetensors b/model-00010-of-00010.safetensors new file mode 100644 index 0000000..0e4d8c8 --- /dev/null +++ b/model-00010-of-00010.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff9d2898a6364dcd57afb65f6050944629a797234a37b03933b5e17287f825a +size 3774959456 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6bac9fb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,371 @@ +{ + "metadata": { + "total_size": 47144806400, + "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..4135d4b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949 +size 17078037 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..caf23df --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "add_prefix_space": null, + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "is_local": false, + "legacy": true, + "local_files_only": false, + "model_max_length": 32768, + "tokenizer_class": "TokenizersBackend", + "unk_token": "", + "use_default_system_prompt": false +}