初始化项目，由ModelHub XC社区提供模型

Model: ccarrillomanzanares/ccmai Source: Original Platform
2026-06-25 08:10:16 +08:00
commit 9bd3abb15a
22 changed files with 52899 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/14
+++ b/14
@@ -0,0 +1,14 @@
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+{{ .Response }}<|im_end|>"""
+
+PARAMETER stop "<|im_start|>"
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "Carlos:"
+PARAMETER stop "CCMAI:"
+PARAMETER temperature 0.3
--- a/README.md
+++ b/README.md
@@ -0,0 +1,38 @@
+---
+language:
+- es
+- en
+license: gemma
+library_name: transformers
+tags:
+- sytem-administration
+- sre
+- linuxpilot
+- gemma3
+- fine-tuned
+base_model: google/gemma-3-27b-it
+model_creator: ccarrillomanzanares
+model_type: gemma3
+pipeline_tag: text-generation
+---
+
+# CCMAI: Sovereign SRE Assistant
+
+**CCMAI** (Carrillo Manzanares Artificial Intelligence) is a fine-tuned version of the **Gemma 3** architecture, specifically optimized for **System Administration, SRE (Site Reliability Engineering), and Linux infrastructure management.**
+
+Built to be the "brain" behind the **LinuxPilot** voice assistant, this model combines high-level reasoning with deep technical knowledge of terminal environments, kernel logs, and cloud infrastructure.
+
+## 🚀 Key Features
+
+* **SRE Specialization:** Trained to analyze logs, suggest kernel fixes, and automate terminal workflows.
+* **Infrastructure Aware:** Optimized for reasoning about complex system architectures and cloud deployments.
+* **Privacy & Sovereignty:** Designed to run locally via **Ollama**, ensuring technical data never leaves your infrastructure.
+* **Gemma 3 Core:** Leverages Google's latest architecture for state-of-the-art performance in reasoning and instruction following.
+
+## 🛠️ Usage
+
+This model is intended for use within the **Ollama** ecosystem or via the **Transformers** library.
+
+### Ollama
+```bash
+ollama run ccarrillomanzanares/ccmai
--- a/README.md.bck
+++ b/README.md.bck
@@ -0,0 +1,132 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- gs://fine-tuning-634768b5-ef69-4ea6-9fd2-c9379a5ee381/copymediadatatask/execution_artifacts/clean_train.jsonl
+model-index:
+- name: tmp/output_dir/gcs/fine-tuning-634768b5-ef69-4ea6-9fd2-c9379a5ee381/postprocess/node-0/checkpoints/final
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.13.0.dev0`
+```yaml
+base_model: gs://vertex-model-garden-restricted-us/gemma3/gemma-3-12b-it
+
+# gemma3 doesn't seem to play nice with ddp
+ddp_find_unused_parameters: true
+experimental_skip_move_to_device: true  # prevent OOM by NOT putting model to GPU before sharding
+
+plugins:
+- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+- axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+
+chat_template: gemma3
+eot_tokens:
+- <end_of_turn>
+
+dataset_prepared_path: last_run_prepared
+output_dir: /workspace/outputs/out
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+
+use_kernels: true
+
+micro_batch_size: 2
+gradient_accumulation_steps: 1
+num_epochs: 3
+optimizer: adamw_torch_fused
+learning_rate: 1e-5
+
+lr_scheduler: cosine
+
+bf16: true
+tf32: true
+logging_steps: 1
+flash_attention: true
+
+gradient_checkpointing: true
+activation_offloading: true
+
+val_set_size: 0
+eval_strategy: "epoch"
+save_strategy: 'no'
+include_tokens_per_second: true
+save_safetensors: true
+use_tensorboard: true
+
+fsdp_version: 1
+fsdp_config:
+  fsdp_limit_all_gathers: true
+  fsdp_sync_module_states: true
+  fsdp_offload_params: true
+  fsdp_use_orig_params: false
+  fsdp_cpu_ram_efficient_loading: true
+  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  fsdp_transformer_layer_cls_to_wrap: Gemma3DecoderLayer
+  fsdp_state_dict_type: SHARDED_STATE_DICT
+  fsdp_sharding_strategy: SHARD_GRAD_OP
+  fsdp_backward_prefetch: BACKWARD_PRE
+  final_state_dict_type: FULL_STATE_DICT
+
+```
+
+</details><br>
+
+# tmp/output_dir/gcs/fine-tuning-634768b5-ef69-4ea6-9fd2-c9379a5ee381/postprocess/node-0/checkpoints/final
+
+This model was trained from scratch on the gs://fine-tuning-634768b5-ef69-4ea6-9fd2-c9379a5ee381/copymediadatatask/execution_artifacts/clean_train.jsonl dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-07
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- training_steps: 675
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.4
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.21.4
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,108 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": 1,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "torch_dtype": "bfloat16",
+    "use_cache": false,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.4",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}
--- a/events.out.tfevents.1775922149.gk3-cml-0411-152311-f717-nap-1xn6t4vl-1a1bcbee-pszh.6465.0
+++ b/events.out.tfevents.1775922149.gk3-cml-0411-152311-f717-nap-1xn6t4vl-1a1bcbee-pszh.6465.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb7787580d8b8333bf991d009faf96781e0093a65dd926b8b320b1acff7d4a6
+size 296246
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.55.4"
+}
--- a/model-00001-of-00005.safetensors
+++ b/model-00001-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8adf417416a66bd4302056fde738bb27c0ff366d1eb0ad9fe4fd2e65683f4fc
+size 4979902192
--- a/model-00002-of-00005.safetensors
+++ b/model-00002-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb74a98beec6dab7aaf6bc8ea518ef0f0f6e697b7dbaccdfc40abccc48b3c903
+size 4931296592
--- a/model-00003-of-00005.safetensors
+++ b/model-00003-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1c49b742cbee685dd1e93dd2684e1c53a2a38fcb67e57426a261e2db6e3b0f
+size 4931296656
--- a/model-00004-of-00005.safetensors
+++ b/model-00004-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329d962843e41ad50f658662d81518075a674d77f7527c5350c8aacbfac9f0a1
+size 4931296656
--- a/model-00005-of-00005.safetensors
+++ b/model-00005-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b862d1c094283a8307ca23f7b723ebd00269cf0a6de31b76672edc9146cf7274
+size 4601000928
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/preprocessor_config.json
+++ b/preprocessor_config.json
@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}
--- a/processor_config.json
+++ b/processor_config.json
@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
--- a/tuning_data_stats.json
+++ b/tuning_data_stats.json