初始化项目，由ModelHub XC社区提供模型

Model: Sorihon/Tempered-Resurgence-24B
Source: Original Platform

.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

README.md

@@ -0,0 +1,41 @@
+---
+base_model:
+- zerofata/MS3.2-PaintedFantasy-v4.1-24B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Magi-JourneyV10
+
+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 [Karcher Mean](https://en.wikipedia.org/wiki/Karcher_mean) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [zerofata/MS3.2-PaintedFantasy-v4.1-24B](https://huggingface.co/zerofata/MS3.2-PaintedFantasy-v4.1-24B)
+* /home/sorihon/Documents/Magi-JourneyV9
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+ models:
+  - model: zerofata/MS3.2-PaintedFantasy-v4.1-24B
+  - model: /home/sorihon/Documents/Magi-JourneyV9
+ merge_method: karcher
+ parameters:
+ tokenizer: 
+   source: union
+ normalize: true
+ int8_mask: true
+ dtype: bfloat16
+
+```

chat_template.jinja

@@ -0,0 +1,51 @@
+{%- 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' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- 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' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] + eos_token }}
+        {%- else %}
+            {{- message['content'][0]['text'] + eos_token }}
+        {%- endif %}
+    {%- 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": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 11,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.0",
+  "use_cache": true,
+  "vocab_size": 131076
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+ models:
+  - model: zerofata/MS3.2-PaintedFantasy-v4.1-24B
+  - model: /home/sorihon/Documents/Magi-JourneyV9
+ merge_method: karcher
+ parameters:
+ tokenizer: 
+   source: union
+ normalize: true
+ int8_mask: true
+ dtype: bfloat16

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec43c144e914c5af51f81ded93e5d532fba9b05aa6f19cd0a693b1f38543978
+size 4907471232

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd24b0bfeb9b14772eeee7762a494783254b1a448cff7ff0854a628b561a6a78
+size 4781592832

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a127fe4a1f7227a34a2ae4c278317d98e6e12f6a2d52481127124d591c0bc50
+size 4781592816

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2abc820adfa0f7679ed1c12c6495c8c4904e2861c05f7b7f1a856f464f5b3c88
+size 4886471592

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20ca65c9b22c4ce55e40708d19b3a54c33ab829ed5d1494d313346c7df2398c
+size 4781592832

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6531dbcea9b8633bfa2e78a19f891e566ebf174cece878e36e6a53a00a549e39
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7609871c7407f030be5d167205623d395898a1bfa68c4e0bce3a821907d67b0
+size 4886471592

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07330a62ef4cba5025005aae3231606fa5bb9f441462d1f59c8ec06b02f0fdb3
+size 4781592832

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0780c096897c98eff78921eb42ac15a1a3cf07f8233074b61fadb5e1f971011
+size 4781592800

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1461996aec9edfa8e8de6f2b13d5f66df5ba8c424385eede585da22d93282b3
+size 3774959456

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 47144888320,
+    "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:f918ab9a8898f5adee8acd367a41d28ff0fa83e1ace4c85f4200cf512e1c1119
+size 17078757

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}