Upload E4B colloquial merged for RunPod vLLM

.gitattributes

@@ -33,3 +33,5 @@ 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
+card_assets/training_curves.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,162 @@
+---
+language:
+- ru
+license: other
+license_name: gemma
+license_link: https://ai.google.dev/gemma/terms
+base_model: google/gemma-4-E4B-it
+pipeline_tag: text-generation
+tags:
+- gemma4
+- russian
+- colloquial
+- style-transfer
+- merged
+- vllm
+library_name: transformers
+datasets:
+- pavelfedortsov/russian-colloquial-sft-50k
+---
+
+# gemma4-e4b-colloquial-ru-merged
+
+*English:* Full-weight **Gemma 4 E4B** checkpoint with colloquial Russian LoRA **merged in** for vLLM / [RunPod Serverless](https://www.runpod.io/serverless). No PEFT at inference time.
+
+## What this model does
+
+Rewrites **formal Russian** into **casual chat-style Russian** (Telegram-like), **without profanity**, while keeping facts, names, numbers, and paragraph structure.
+
+**Not** a general chat model — use the instruction prefix from training (see below).
+
+## Model lineage
+
+| Stage | Artifact |
+|-------|----------|
+| Base | [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it) |
+| LoRA (SFT) | [pavelfedortsov/gemma4-e4b-lora-colloquial-ru](https://huggingface.co/pavelfedortsov/gemma4-e4b-lora-colloquial-ru) |
+| **This repo** | LoRA merged into base + vLLM fixes (`k_norm`, processor configs) |
+
+Merge was done with `peft.merge_and_unload()`; missing `language_model` **k_norm** weights for layers 24–41 were copied from the base checkpoint (required for vLLM).
+
+## Training data
+
+- **50,000** SFT pairs, mat-free colloquial style  
+- Hub dataset: [pavelfedortsov/russian-colloquial-sft-50k](https://huggingface.co/datasets/pavelfedortsov/russian-colloquial-sft-50k)  
+- Built from [kurumikz/telegram-corpus-russian-kazakh](https://huggingface.co/datasets/kurumikz/telegram-corpus-russian-kazakh) + Gemini pair generation (see dataset card)
+
+**User prompt template (training & inference):**
+
+```
+Перепиши простым разговорным русским, как в переписке. Без мата и грубости. Сохрани смысл:
+<формальный текст>
+```
+
+## Training configuration (LoRA → merge)
+
+Config file (also in `card_assets/train_colloquial_e4b_gpu.yaml`):
+
+| Parameter | Value |
+|-----------|--------|
+| Base model | `google/gemma-4-E4B-it` |
+| Method | LoRA on language tower (`model.language_model.*`) |
+| LoRA rank / alpha | **32 / 64** |
+| Target modules | `q,k,v,o` + MLP (`gate, up, down`) |
+| Dataset | 50k × 1 repeat |
+| Epochs | **2** (12,500 optimizer steps) |
+| Seq length | 512 |
+| Batch | 1 × grad accum **8** (effective 8) |
+| LR | 1e-4, cosine, warmup 3% |
+| Precision | bf16, gradient checkpointing |
+| Loss | assistant-only |
+| Hardware | RunPod **A100 80GB** |
+
+## Training metrics (LoRA run)
+
+![Training curves](card_assets/training_curves.png)
+
+| Metric | Start (step ~25) | End (step 12,500) | Best |
+|--------|------------------|-------------------|------|
+| `loss` | ~3.42 | ~0.81 | **~0.67** |
+| `mean_token_accuracy` | ~0.63 | ~0.82 | **~0.84** |
+
+Checkpoints saved every 1000 steps under the LoRA adapter repo.
+
+## Inference
+
+### RunPod Serverless (vLLM)
+
+```env
+MODEL_NAME=pavelfedortsov/gemma4-e4b-colloquial-ru-merged
+HF_TOKEN=<your_token>
+TRUST_REMOTE_CODE=true
+DTYPE=bfloat16
+MAX_MODEL_LEN=4096
+GPU_MEMORY_UTILIZATION=0.90
+ENFORCE_EAGER=true
+ENABLE_LORA=false
+LANGUAGE_MODEL_ONLY=true
+LIMIT_MM_PER_PROMPT={"image":0,"audio":0,"video":0}
+```
+
+Recommended GPU: **≥40 GB** VRAM (merged ~32 GB weights in bf16).
+
+### Transformers (local)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "pavelfedortsov/gemma4-e4b-colloquial-ru-merged"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+formal = "Сегодня на совещании обсуждали внедрение новой версии API."
+user = (
+    "Перепиши простым разговорным русским, как в переписке. "
+    "Без мата и грубости. Сохрани смысл:\n"
+    f"{formal}"
+)
+messages = [{"role": "user", "content": user}]
+prompt = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9)
+print(tokenizer.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
+
+### OpenAI-compatible API (RunPod / vLLM)
+
+```bash
+curl "$RUNPOD_URL/v1/chat/completions" \
+  -H "Authorization: Bearer $RUNPOD_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "pavelfedortsov/gemma4-e4b-colloquial-ru-merged",
+    "messages": [{
+      "role": "user",
+      "content": "Перепиши простым разговорным русским, как в переписке. Без мата и грубости. Сохрани смысл:\nВаш формальный т��кст."
+    }],
+    "max_tokens": 512,
+    "temperature": 0.7
+  }'
+```
+
+## Limitations
+
+- [Gemma license](https://ai.google.dev/gemma/terms) applies to the base architecture and weights.
+- Quality varies on long news-style text; model may shorten or paraphrase aggressively.
+- Not safety-tuned for production without your own evaluation.
+- Merged vs LoRA inference can differ slightly in style.
+
+## Related repos
+
+| Resource | Link |
+|----------|------|
+| LoRA adapter | https://huggingface.co/pavelfedortsov/gemma4-e4b-lora-colloquial-ru |
+| Dataset (50k) | https://huggingface.co/datasets/pavelfedortsov/russian-colloquial-sft-50k |
+| Base model | https://huggingface.co/google/gemma-4-E4B-it |

card_assets/train_colloquial_e4b_gpu.yaml

@@ -0,0 +1,40 @@
+# Colloquial SFT: google/gemma-4-E4B-it, 50k pairs (data/russian_colloquial_sft.jsonl)
+# GPU 24GB+: batch 1 + grad accum 8. RunPod: scripts/run_train_colloquial_e4b_gpu.sh
+model_id: google/gemma-4-E4B-it
+
+dataset_path: data/russian_colloquial_sft.jsonl
+dataset_repeats: 1
+
+max_seq_length: 512
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+num_train_epochs: 2
+learning_rate: 1.0e-4
+warmup_ratio: 0.03
+lr_scheduler_type: cosine
+
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+  - gate_proj
+  - up_proj
+  - down_proj
+
+gradient_checkpointing: true
+use_cache: false
+bf16: true
+fp16: false
+
+device: auto
+logging_steps: 25
+save_strategy: steps
+save_steps: 1000
+packing: false
+
+output_dir: outputs/gemma4-e4b-lora-colloquial-ru
+assistant_only_loss: true

chat_template.jinja

@@ -0,0 +1,16 @@
+{#- Text-only training template for Gemma 4 (E2B) with assistant-only loss. -#}
+{{ bos_token }}
+{%- for message in messages -%}
+    {%- if message['role'] == 'assistant' -%}
+{{ '<|turn>model\n' }}{% generation %}{{ message['content'] | trim }}{{ '<turn|>\n' }}{% endgeneration %}
+    {%- elif message['role'] == 'user' -%}
+{{ '<|turn>user\n' }}{{ message['content'] | trim }}{{ '<turn|>\n' }}
+    {%- elif message['role'] == 'system' -%}
+{{ '<|turn>user\n' }}{{ message['content'] | trim }}{{ '<turn|>\n' }}
+    {%- else -%}
+{{ raise_exception('Unsupported role: ' ~ message['role']) }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+{{ '<|turn>model\n' }}
+{%- endif -%}

config.json

@@ -0,0 +1,198 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "float32",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "float32",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "float32",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "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"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "float32",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0.dev0"
+}

image_processor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "image_processor_type": "Gemma4ImageProcessor",
+  "image_seq_length": 280,
+  "image_std": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "max_soft_tokens": 280,
+  "patch_size": 16,
+  "pooling_kernel_size": 3,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd8aa751975c345fb7ccff75b88b0b4590d7d8e7bfb2c146ad06230ad43b919
+size 31764692904

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "dither": 0.0,
+  "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+  "feature_size": 128,
+  "fft_length": 512,
+  "fft_overdrive": false,
+  "frame_length": 320,
+  "hop_length": 160,
+  "input_scale_factor": 1.0,
+  "max_frequency": 8000.0,
+  "mel_floor": 0.001,
+  "min_frequency": 0.0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "per_bin_mean": null,
+  "per_bin_stddev": null,
+  "preemphasis": 0.0,
+  "preemphasis_htk_flavor": true,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

tokenizer_config.json

@@ -0,0 +1,96 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

video_processor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "image_mean": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "image_std": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "max_soft_tokens": 70,
+  "num_frames": 32,
+  "patch_size": 16,
+  "pooling_kernel_size": 3,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "video_processor_type": "Gemma4VideoProcessor"
+}