commit b0ddf2b1b8595923de256c413029e3336cca1213 Author: ModelHub XC Date: Thu Jul 9 08:57:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Phani1479432/rocky-gemma-2b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5047ec8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,40 @@ +*.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 +rocky-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +rocky-f16.gguf filter=lfs diff=lfs merge=lfs -text +rocky.task filter=lfs diff=lfs merge=lfs -text +rocky.litertlm filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..7d96b4a --- /dev/null +++ b/Modelfile @@ -0,0 +1,14 @@ +FROM hf.co/Phani1479432/rocky-gemma-2b:rocky-q4_k_m.gguf + +# Custom template to match Gemma 2 formatting and Rocky training prefix +TEMPLATE """{{- if .Prompt }}user +Speak like Rocky. + +{{ .Prompt }} +{{- end }}model +{{ .Response }} +""" + +# Set stop tokens +PARAMETER stop "" +PARAMETER stop "" diff --git a/README.md b/README.md new file mode 100644 index 0000000..23b5299 --- /dev/null +++ b/README.md @@ -0,0 +1,44 @@ +--- +license: gemma +library_name: mlx +pipeline_tag: text-generation +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +extra_gated_button_content: Acknowledge license +tags: +- conversational +- mlx +- ollama +base_model: google/gemma-2-2b-it +--- + +# Rocky Gemma 2B (It) + +Rocky Gemma 2B is a fine-tuned model based on `google/gemma-2-2b-it`, customized to speak and act like Rocky. + +## 🦙 Run with Ollama + +You can download and run this model instantly on your local Ollama instance with a single command: + +```bash +curl -sSL https://huggingface.co/Phani1479432/rocky-gemma-2b/raw/main/Modelfile | ollama create rocky -f - && ollama run rocky +``` + +### What this command does: +1. **Downloads the Modelfile**: Fetches the custom configuration specifying stop parameters and formatting templates directly from Hugging Face. +2. **Creates the Model locally**: Registers a new local model named `rocky` in Ollama. +3. **Downloads the GGUF Weights**: Automatically pulls the quantized GGUF weights (`rocky-q4_k_m.gguf`) directly from Hugging Face. +4. **Starts the Chat**: Launches an interactive shell session for you to chat with Rocky. + +--- + +## ⚡ Run with MLX + +If you are on Apple Silicon, you can use the MLX library to run the fused model weights: + +```bash +pip install mlx-lm +python -m mlx_lm.generate --model Phani1479432/rocky-gemma-2b --prompt "Hey Rocky, what's your training routine like?" +``` diff --git a/adapters/0000100_adapters.safetensors b/adapters/0000100_adapters.safetensors new file mode 100644 index 0000000..9eeda6d --- /dev/null +++ b/adapters/0000100_adapters.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a129ecd35562211720e32425426f21e0096bb43fd8b83acea586059c904bd72 +size 25583156 diff --git a/adapters/0000200_adapters.safetensors b/adapters/0000200_adapters.safetensors new file mode 100644 index 0000000..343fd40 --- /dev/null +++ b/adapters/0000200_adapters.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:533df00e0e1df5c3eaef288ca78e6c75e01982108ab8a3493d494121987d5416 +size 25583156 diff --git a/adapters/0000300_adapters.safetensors b/adapters/0000300_adapters.safetensors new file mode 100644 index 0000000..baddd3e --- /dev/null +++ b/adapters/0000300_adapters.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5235509e18f79a9670c97fb517bb365596c2d077a1e686b4e55017c03897b6 +size 25583156 diff --git a/adapters/0000400_adapters.safetensors b/adapters/0000400_adapters.safetensors new file mode 100644 index 0000000..8536033 --- /dev/null +++ b/adapters/0000400_adapters.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5270c5dd9484ef757f7f8a987858573d32be7cea1e9a7967c77dbe6cbe9a734 +size 25583156 diff --git a/adapters/0000500_adapters.safetensors b/adapters/0000500_adapters.safetensors new file mode 100644 index 0000000..af3c7ee --- /dev/null +++ b/adapters/0000500_adapters.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b09f1d33b3c8d10fc706c3c57f52a694b47000d605c9738a95aabbb5146e201 +size 25583156 diff --git a/adapters/0000600_adapters.safetensors b/adapters/0000600_adapters.safetensors new file mode 100644 index 0000000..bfe2092 --- /dev/null +++ b/adapters/0000600_adapters.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1695d857bf8e7410d5cdd393ff3ea281923d176442e47c1da1763ceb051837e +size 25583156 diff --git a/adapters/adapter_config.json b/adapters/adapter_config.json new file mode 100644 index 0000000..0b6d6cb --- /dev/null +++ b/adapters/adapter_config.json @@ -0,0 +1,41 @@ +{ + "adapter_path": "./adapters", + "batch_size": 2, + "clear_cache_threshold": 0, + "config": null, + "data": "./rocky_data", + "fine_tune_type": "lora", + "grad_accumulation_steps": 1, + "grad_checkpoint": false, + "iters": 600, + "learning_rate": 1e-05, + "lora_parameters": { + "rank": 8, + "dropout": 0.0, + "scale": 20.0 + }, + "lr_schedule": null, + "mask_prompt": false, + "max_seq_length": 2048, + "model": "google/gemma-2-2b-it", + "num_layers": 16, + "optimizer": "adam", + "optimizer_config": { + "adam": {}, + "adamw": {}, + "muon": {}, + "sgd": {}, + "adafactor": {} + }, + "project_name": null, + "report_to": null, + "resume_adapter_file": null, + "save_every": 100, + "seed": 0, + "steps_per_eval": 50, + "steps_per_report": 10, + "test": false, + "test_batches": 500, + "train": true, + "val_batches": 25 +} \ No newline at end of file diff --git a/adapters/adapters.safetensors b/adapters/adapters.safetensors new file mode 100644 index 0000000..bfe2092 --- /dev/null +++ b/adapters/adapters.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1695d857bf8e7410d5cdd393ff3ea281923d176442e47c1da1763ceb051837e +size 25583156 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..923ec25 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{{ bos_token }}{% 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 + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..02b637b --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": [ + 1, + 107 + ], + "final_logit_softcapping": 30.0, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2304, + "initializer_range": 0.02, + "intermediate_size": 9216, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 8, + "num_hidden_layers": 26, + "num_key_value_heads": 4, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.42.4", + "use_cache": true, + "vocab_size": 256000 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2da7d77 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": [ + 1, + 107 + ], + "pad_token_id": 0, + "transformers_version": "4.42.4" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..7b3cffe --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88582595a82016e9e50a0ae57c24d7931e1c1509ea752990884cb64f71687ba4 +size 5228717351 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..1696977 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,296 @@ +{ + "metadata": { + "total_size": 5228683776, + "total_parameters": 2614341888 + }, + "weight_map": { + "model.embed_tokens.weight": "model.safetensors", + "model.layers.0.input_layernorm.weight": "model.safetensors", + "model.layers.0.mlp.down_proj.weight": "model.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model.safetensors", + "model.layers.0.mlp.up_proj.weight": "model.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model.safetensors", + "model.layers.0.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model.safetensors", + "model.layers.1.input_layernorm.weight": "model.safetensors", + "model.layers.1.mlp.down_proj.weight": "model.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model.safetensors", + "model.layers.1.mlp.up_proj.weight": "model.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model.safetensors", + "model.layers.1.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model.safetensors", + "model.layers.10.input_layernorm.weight": "model.safetensors", + "model.layers.10.mlp.down_proj.weight": "model.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model.safetensors", + "model.layers.10.mlp.up_proj.weight": "model.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model.safetensors", + "model.layers.10.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model.safetensors", + "model.layers.11.input_layernorm.weight": "model.safetensors", + "model.layers.11.mlp.down_proj.weight": "model.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model.safetensors", + "model.layers.11.mlp.up_proj.weight": "model.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model.safetensors", + "model.layers.11.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model.safetensors", + "model.layers.12.input_layernorm.weight": "model.safetensors", + "model.layers.12.mlp.down_proj.weight": "model.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model.safetensors", + "model.layers.12.mlp.up_proj.weight": "model.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model.safetensors", + "model.layers.12.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model.safetensors", + "model.layers.13.input_layernorm.weight": "model.safetensors", + "model.layers.13.mlp.down_proj.weight": "model.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model.safetensors", + "model.layers.13.mlp.up_proj.weight": "model.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model.safetensors", + "model.layers.13.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model.safetensors", + "model.layers.14.input_layernorm.weight": "model.safetensors", + "model.layers.14.mlp.down_proj.weight": "model.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model.safetensors", + "model.layers.14.mlp.up_proj.weight": "model.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model.safetensors", + "model.layers.14.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model.safetensors", + "model.layers.15.input_layernorm.weight": "model.safetensors", + "model.layers.15.mlp.down_proj.weight": "model.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model.safetensors", + "model.layers.15.mlp.up_proj.weight": "model.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model.safetensors", + "model.layers.15.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model.safetensors", + "model.layers.16.input_layernorm.weight": "model.safetensors", + "model.layers.16.mlp.down_proj.weight": "model.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model.safetensors", + "model.layers.16.mlp.up_proj.weight": "model.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model.safetensors", + "model.layers.16.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model.safetensors", + "model.layers.17.input_layernorm.weight": "model.safetensors", + "model.layers.17.mlp.down_proj.weight": "model.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model.safetensors", + "model.layers.17.mlp.up_proj.weight": "model.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model.safetensors", + "model.layers.17.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model.safetensors", + "model.layers.18.input_layernorm.weight": "model.safetensors", + "model.layers.18.mlp.down_proj.weight": "model.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model.safetensors", + "model.layers.18.mlp.up_proj.weight": "model.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model.safetensors", + "model.layers.18.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.18.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model.safetensors", + "model.layers.19.input_layernorm.weight": "model.safetensors", + "model.layers.19.mlp.down_proj.weight": "model.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model.safetensors", + "model.layers.19.mlp.up_proj.weight": "model.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model.safetensors", + "model.layers.19.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.19.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model.safetensors", + "model.layers.2.input_layernorm.weight": "model.safetensors", + "model.layers.2.mlp.down_proj.weight": "model.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model.safetensors", + "model.layers.2.mlp.up_proj.weight": "model.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model.safetensors", + "model.layers.2.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model.safetensors", + "model.layers.20.input_layernorm.weight": "model.safetensors", + "model.layers.20.mlp.down_proj.weight": "model.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model.safetensors", + "model.layers.20.mlp.up_proj.weight": "model.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model.safetensors", + "model.layers.20.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.20.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model.safetensors", + "model.layers.21.input_layernorm.weight": "model.safetensors", + "model.layers.21.mlp.down_proj.weight": "model.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model.safetensors", + "model.layers.21.mlp.up_proj.weight": "model.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model.safetensors", + "model.layers.21.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.21.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model.safetensors", + "model.layers.22.input_layernorm.weight": "model.safetensors", + "model.layers.22.mlp.down_proj.weight": "model.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model.safetensors", + "model.layers.22.mlp.up_proj.weight": "model.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model.safetensors", + "model.layers.22.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.22.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model.safetensors", + "model.layers.23.input_layernorm.weight": "model.safetensors", + "model.layers.23.mlp.down_proj.weight": "model.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model.safetensors", + "model.layers.23.mlp.up_proj.weight": "model.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model.safetensors", + "model.layers.23.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.23.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model.safetensors", + "model.layers.24.input_layernorm.weight": "model.safetensors", + "model.layers.24.mlp.down_proj.weight": "model.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model.safetensors", + "model.layers.24.mlp.up_proj.weight": "model.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model.safetensors", + "model.layers.24.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.24.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model.safetensors", + "model.layers.25.input_layernorm.weight": "model.safetensors", + "model.layers.25.mlp.down_proj.weight": "model.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model.safetensors", + "model.layers.25.mlp.up_proj.weight": "model.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model.safetensors", + "model.layers.25.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.25.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model.safetensors", + "model.layers.3.input_layernorm.weight": "model.safetensors", + "model.layers.3.mlp.down_proj.weight": "model.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model.safetensors", + "model.layers.3.mlp.up_proj.weight": "model.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model.safetensors", + "model.layers.3.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model.safetensors", + "model.layers.4.input_layernorm.weight": "model.safetensors", + "model.layers.4.mlp.down_proj.weight": "model.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model.safetensors", + "model.layers.4.mlp.up_proj.weight": "model.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model.safetensors", + "model.layers.4.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model.safetensors", + "model.layers.5.input_layernorm.weight": "model.safetensors", + "model.layers.5.mlp.down_proj.weight": "model.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model.safetensors", + "model.layers.5.mlp.up_proj.weight": "model.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model.safetensors", + "model.layers.5.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model.safetensors", + "model.layers.6.input_layernorm.weight": "model.safetensors", + "model.layers.6.mlp.down_proj.weight": "model.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model.safetensors", + "model.layers.6.mlp.up_proj.weight": "model.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model.safetensors", + "model.layers.6.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model.safetensors", + "model.layers.7.input_layernorm.weight": "model.safetensors", + "model.layers.7.mlp.down_proj.weight": "model.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model.safetensors", + "model.layers.7.mlp.up_proj.weight": "model.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model.safetensors", + "model.layers.7.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model.safetensors", + "model.layers.8.input_layernorm.weight": "model.safetensors", + "model.layers.8.mlp.down_proj.weight": "model.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model.safetensors", + "model.layers.8.mlp.up_proj.weight": "model.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model.safetensors", + "model.layers.8.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model.safetensors", + "model.layers.9.input_layernorm.weight": "model.safetensors", + "model.layers.9.mlp.down_proj.weight": "model.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model.safetensors", + "model.layers.9.mlp.up_proj.weight": "model.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model.safetensors", + "model.layers.9.post_feedforward_layernorm.weight": "model.safetensors", + "model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model.safetensors", + "model.norm.weight": "model.safetensors" + } +} \ No newline at end of file diff --git a/rocky-f16.gguf b/rocky-f16.gguf new file mode 100644 index 0000000..eee4fbb --- /dev/null +++ b/rocky-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4918158ade46b7961259cf57fda4727e498a87fe4fee47286fe52b63c44e226 +size 5235215168 diff --git a/rocky-q4_k_m.gguf b/rocky-q4_k_m.gguf new file mode 100644 index 0000000..d83c5a3 --- /dev/null +++ b/rocky-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a67725cfe6cd771540a4d892b0b79b878339a5cfe48d4351e184a5dd9d26f14 +size 1708583744 diff --git a/rocky.litertlm b/rocky.litertlm new file mode 100644 index 0000000..4ffb8ac --- /dev/null +++ b/rocky.litertlm @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25be252d6d9f9fde24ce76232b0c77a04b4c40d05a7fdefd2b3dab82e2cb23a1 +size 1316165376 diff --git a/rocky.task b/rocky.task new file mode 100644 index 0000000..4ffb8ac --- /dev/null +++ b/rocky.task @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25be252d6d9f9fde24ce76232b0c77a04b4c40d05a7fdefd2b3dab82e2cb23a1 +size 1316165376 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..a2c58e3 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487cee8724215dcd2dde8888539e8b1bf844ceb5dbbe27f7845abda69eeb060f +size 34362872 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..796efe9 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..e32d395 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,20 @@ +{ + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": [ + "", + "" + ], + "is_local": true, + "local_files_only": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}