Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,54 @@
+---
+base_model:
+- Naphula-Archives/Acid2501-24B
+- mistralai/Mistral-Small-Instruct-2501
+- Casual-Autopsy/RP-Spectrum-24B
+- TheDrummer/Rivermind-24B-v1
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Sakura-24B-Consistent-Brain
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [mistralai/Mistral-Small-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-Instruct-2501) as a 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/Rivermind-24B-v1](https://huggingface.co/TheDrummer/Rivermind-24B-v1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+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/Rivermind-24B-v1
+    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
+
+```

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 %}

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
+}

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/Rivermind-24B-v1
+    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

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b2ba245a4da076ecfdec37ab0ad46955a19b5606fb5aa4d87ddceb60323f09
+size 4907389312

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c950c82303b5522386b31bf74550dae891bb887a17e7ebcb01cf866e6a6705a8
+size 4781592832

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1789c091c69567598a3555eba5fea39969bb99bcf03cf93566b2203ef9331e69
+size 4781592816

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7ce1ce1dc50c349aa21e69bc083f483e2013224fe6c3a754131efcda969d2c
+size 4886471592

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d6da7c484541d8cdee6b65ec388357f701b90bc096ab183d955abed131204c
+size 4781592832

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258cc7f7e41545dad8de5982da0b63fd845507fc5079f97782a8706c943a915d
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6492c5d7ce8e6d75703f2b5826417fe7f287191fcc7027703dcf9413b893d3ef
+size 4886471592

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea3d1c23af9db35f3c3720bd625cbac4874b757bd4cd9853fd8ed817c09a798
+size 4781592832

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd324c2156c3b80673a13c8f8190a7c857c4e70499b438d6a92e9304a355276
+size 4781592800

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c750afb2a321612b7d6b94a482b7cd059ff6a19434aa315b59e1f1583a71021
+size 3774959456

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"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}