commit 59a332c5e02837321d384c280b108b067179afca Author: ModelHub XC Date: Sun Jun 7 09:33:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: abideen/gemma-2b-openhermes Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0e2c444 --- /dev/null +++ b/README.md @@ -0,0 +1,283 @@ +--- +license: cc-by-nc-4.0 +base_model: google/gemma-2b-it +tags: +- generated_from_trainer +- axolotl +- gemma +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- distillation +model-index: +- name: gemma-2b-openhermes + results: [] +datasets: +- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha +language: +- en +library_name: transformers +pipeline_tag: text-generation +--- + + +# gemma-2b-openhermes + + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/9bmxL8Lt7hBaKlKHVxtew.jpeg) + +gemma-2b-openhermes is a variant of the Gemma 2B language model, which has been further fine-tuned on the OpenHermes-2.5 preference dataset +using QLoRA. + + +* [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) +* [mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha](https://huggingface.co/datasets/mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha) + +
+ +## Usage + +### Chat Template + +The instruction-tuned models use a chat template that must be adhered to for conversational use. +The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet. + +Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction: + +```py +from transformers import AutoTokenizer, AutoModelForCausalLM +import transformers +import torch + +model_id = "abideen/gemma-2b-openhermes" +dtype = torch.bfloat16 + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + device_map="cuda", + torch_dtype=dtype, +) + +chat = [{ "role": "user", "content": "What is a Language Model?" }] +prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) +``` + +After the prompt is ready, generation can be performed like this: + +```py +inputs = tokenizer.encode(prompt, add_special_tokens=True, return_tensors="pt") +outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=250) +print(tokenizer.decode(outputs[0])) +``` + +### Inputs and outputs + +* **Input:** Text string, such as a question, a prompt, or a document to be + summarized. +* **Output:** Generated English-language text in response to the input, such + as an answer to a question, or a summary of a document. + +## 🏆 Evaluation results + +# Nous Benchmark + +Agieval + +| Task | Version | Metric | Value | | StdErr | +|-------------------------------------------|---------|--------|-------|---|---------| +| agieval\_aqua\_rat | 0 | acc | 24.02 | _ | 2.69 | +| agieval\_aqua\_rat | 0 | acc\_norm | 24.02 | _ | 2.69 | +| agieval\_logiqa\_en | 0 | acc | 23.20 | _ | 1.66 | +| agieval\_logiqa\_en | 0 | acc\_norm | 24.42 | _ | 1.69 | +| agieval\_lsat\_ar | 0 | acc | 18.26 | _ | 2.55 | +| agieval\_lsat\_ar | 0 | acc\_norm | 18.70 | _ | 2.58 | +| agieval\_lsat\_lr | 0 | acc | 22.35 | _ | 1.85 | +| agieval\_lsat\_lr | 0 | acc\_norm | 23.53 | _ | 1.88 | +| agieval\_lsat\_rc | 0 | acc | 20.82 | _ | 2.48 | +| agieval\_lsat\_rc | 0 | acc\_norm | 20.07 | _ | 2.45 | +| agieval\_sat\_en | 0 | acc | 32.52 | _ | 3.27 | +| agieval\_sat\_en | 0 | acc\_norm | 32.52 | _ | 3.27 | +| agieval\_sat\_en\_without\_passage | 0 | acc | 25.73 | _ | 3.05 | +| agieval\_sat\_en\_without\_passage | 0 | acc\_norm | 24.27 | _ | 2.99 | +| agieval\_sat\_math | 0 | acc | 25.00 | _ | 2.93 | +| agieval\_sat\_math | 0 | acc\_norm | 20.91 | _ | 2.75 | +Average: 24.11 + +GPT4ALL + +| Task | Version | Metric | Value | | StdErr | +|----------------------|---------|--------|-------|---|---------| +| arc\_challenge | 0 | acc | 21.77 | _ | 1.21 | +| arc\_challenge | 0 | acc\_norm | 24.15 | _ | 1.25 | +| arc\_easy | 0 | acc | 37.37 | _ | 0.99 | +| arc\_easy | 0 | acc\_norm | 36.95 | _ | 0.99 | +| boolq | 1 | acc | 65.60 | _ | 0.83 | +| hellaswag | 0 | acc | 34.54 | _ | 0.47 | +| hellaswag | 0 | acc\_norm | 40.54 | _ | 0.49 | +| openbookqa | 0 | acc | 15.00 | _ | 1.59 | +| openbookqa | 0 | acc\_norm | 27.40 | _ | 2.00 | +| piqa | 0 | acc | 60.88 | _ | 1.14 | +| piqa | 0 | acc\_norm | 60.55 | _ | 1.14 | +| winogrande | 0 | acc | 50.91 | _ | 1.41 | +Average: 40.01 + +BigBench + +| Task | Version | Metric | Value | Std Err | +|-----------------------------------|---------|--------|--------|---------| +| bigbench\_causal\_judgement | 0 | MCG | 50 | 2.26 | +| bigbench\_date\_understanding | 0 | MCG | 49.14 | 2.18 | +| bigbench\_disambiguation\_qa | 0 | MCG | 49.31 | 2.74 | +| bigbench\_geometric\_shapes | 0 | MCG | 14.18 | 1.37 | +| bigbench\_logical\_deduction\_5objs | 0 | MCG | 49.41 | 2.73 | +| bigbench\_logical\_deduction\_7objs | 0 | MCG | 41.48 | 2.46 | +| bigbench\_logical\_deduction\_3objs | 0 | MCG | 69.33 | 2.75 | +| bigbench\_movie\_recommendation | 0 | MCG | 51.71 | 2.25 | +| bigbench\_navigate | 0 | MCG | 50 | 1.58 | +| bigbench\_reasoning\_colored\_obj | 0 | MCG | 51.92 | 0.99 | +| bigbench\_ruin\_names | 0 | MCG | 48.14 | 2.01 | +| bigbench\_salient\_trans\_err\_detec | 0 | MCG | 39.92 | 1.2 | +| bigbench\_snarks | 0 | MCG | 64.14 | 3.71 | +| bigbench\_sports\_understanding | 0 | MCG | 55.31 | 1.59 | +| bigbench\_temporal\_sequences | 0 | MCG | 46.92 | 1.4 | +| bigbench\_tsk\_shuff\_objs\_5 | 0 | MCG | 25.04 | 1.01 | +| bigbench\_tsk\_shuff\_objs\_7 | 0 | MCG | 15.04 | 0.72 | +| bigbench\_tsk\_shuff\_objs\_3 | 0 | MCG | 55.33 | 2.75 | +Average: 44.75 + +TruthfulQA + +| Task | Version | Metric | Value | Std Err | +|----------------------------------|---------|--------|--------|----------| +| truthfulqa\_mc | 1 | mc1 | 30.11 | 1.61 | +| truthfulqa\_mc | 1 | mc2 | 47.69 | 1.61 | +Average: 38.90 + + +# Openllm Benchmark + +| Task |Version| Metric |Value| |Stderr| +|-------------|------:|--------|----:|---|-----:| +|arc_challenge| 0|acc |40.44|± | 1.43| +| | |acc_norm|43.81|± | 1.34| +|hellaswag | 0|acc |48.1 |± | 0.45| +| | |acc_norm|62.73|± | 0.32| +|gsm8k | 0|acc |5.6 |± | 0.6 | +|winogrande | 0|acc |60.91|± | 1.3 | +|mmlu | 0|acc |37.62 |±| 0.6 | + +Average: 73.5% + +### TruthfulQA +| Task |Version|Metric|Value| |Stderr| +|-------------|------:|------|----:|---|-----:| +|truthfulqa_mc| 1|mc1 |29.00|± | 1.58| +| | |mc2 |45.83|± | 1.59| + + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-07 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 8 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 100 +- training_steps: 1300 + + +### 📝 Axolotl Configuration + +```yaml +base_model: google/gemma-2b-it +model_type: GemmaForCausalLM +tokenizer_type: GemmaTokenizer +trust_remote_code: true + +load_in_8bit: false +load_in_4bit: true +strict: false + +rl: dpo +chat_template: chatml +datasets: + - path: mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha + split: train + type: chatml.intel +dataset_prepared_path: +val_set_size: 0.01 +output_dir: ./out + +adapter: qlora +lora_model_dir: + +sequence_len: 1800 +sample_packing: false +pad_to_sequence_len: false + +lora_r: 16 +lora_alpha: 16 +lora_dropout: 0.05 +lora_target_linear: true +lora_fan_in_fan_out: +lora_target_modules: + +wandb_project: gemma +wandb_entity: +wandb_watch: +wandb_name: +wandb_log_model: + +gradient_accumulation_steps: 8 +micro_batch_size: 1 +num_epochs: 1 +optimizer: paged_adamw_32bit +lr_scheduler: cosine +learning_rate: 5e-7 + +train_on_inputs: false +group_by_length: false +bf16: true +fp16: false +tf32: true + +gradient_checkpointing: true +early_stopping_patience: +resume_from_checkpoint: +local_rank: +logging_steps: 1 +xformers_attention: +flash_attention: false + +warmup_steps: 100 +evals_per_epoch: 1 +eval_table_size: +eval_table_max_new_tokens: 128 +save_steps: 1000 +max_steps: 1300 +debug: +deepspeed: +weight_decay: 0.0 +fsdp: +fsdp_config: +special_tokens: +``` + + +### Framework versions + +- Transformers 4.39.0.dev0 +- Pytorch 2.1.2+cu118 +- Datasets 2.17.0 +- Tokenizers 0.15.0 +- axolotl: 0.4.0 + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6571a7e --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "google/gemma-2b-it", + "architectures": [ + "GemmaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "eos_token_id": 1, + "head_dim": 256, + "hidden_act": "gelu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 8192, + "model_type": "gemma", + "num_attention_heads": 8, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "torch_dtype": "float16", + "transformers_version": "4.39.0.dev0", + "use_cache": true, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1f9785c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.39.0.dev0" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..2d938a8 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfcc3cb85f1f62e3a0b0e3890e5a3ac6e8f7ba90d13da540bfd21f8e251d3718 +size 4945242104 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..c195730 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cfc80ceba0cdb592050a92d4f04ca6b56d0fd9c003b3750e9f5ddeef3a0731d +size 67121600 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b8fcee9 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,171 @@ +{ + "metadata": { + "total_size": 5012344832 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..8d6368f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..10d1ca0 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee +size 17477929 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..0fb99fa --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef +size 4241111 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..f66eacb --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,70 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in 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 %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": null, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}