commit 07127161ee76494016c90d32a93aea1006d33ec2 Author: ModelHub XC Date: Wed Sep 9 14:27:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: chorgle/dylama Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33daa12 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +Meta-Llama-3.1-8B-Instruct-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-abliterated.F16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3.1-8B-Instruct-abliterated.F16.gguf b/Meta-Llama-3.1-8B-Instruct-abliterated.F16.gguf new file mode 100644 index 0000000..0549371 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-abliterated.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36330d0f27e730c910a4c2fa4b953f958127640fec17e43a9a5e36eb731373e +size 16068892352 diff --git a/Meta-Llama-3.1-8B-Instruct-abliterated.Q4_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-abliterated.Q4_K_M.gguf new file mode 100644 index 0000000..5502bbc --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-abliterated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe6a6528521a79dd9f808b9775ec86333feffef08eac846d6ec8e531fe17c51 +size 4920735424 diff --git a/Meta-Llama-3.1-8B-Instruct-abliterated.Q8_0.gguf b/Meta-Llama-3.1-8B-Instruct-abliterated.Q8_0.gguf new file mode 100644 index 0000000..146c68c --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-abliterated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf9d290f48bc6b04d7d2cca271977e7803f826091374ba69783b780538871a69 +size 8540772032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5f1fea --- /dev/null +++ b/README.md @@ -0,0 +1,25 @@ +--- +tags: +- gguf +- llama.cpp +- unsloth + +--- + +# dylama : GGUF + +this model was trained off unhinged quotes from my friend + +This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth). + +**Example usage**: +- For text only LLMs: `./llama.cpp/llama-cli -hf chorgle/dylama --jinja` +- For multimodal models: `./llama.cpp/llama-mtmd-cli -hf chorgle/dylama --jinja` + +## Available Model files: +- `Meta-Llama-3.1-8B-Instruct-abliterated.Q4_K_M.gguf` + +## Note +The model's BOS token behavior was adjusted for GGUF compatibility. +This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) +[](https://github.com/unslothai/unsloth) diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000..939ea16 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,50 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "LlamaForCausalLM", + "parent_library": "transformers.models.llama.modeling_llama", + "unsloth_fixed": true + }, + "base_model_name_or_path": "mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "o_proj", + "down_proj", + "k_proj", + "v_proj", + "gate_proj", + "q_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000..436dbb5 --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423d79ce890883c459513ac040dbc5fb77e6d278b869ee38cca34c41b1202679 +size 167832240 diff --git a/config.json b/config.json new file mode 100644 index 0000000..8f74e3f --- /dev/null +++ b/config.json @@ -0,0 +1,37 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "torch_dtype": "float16", + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128004, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "transformers_version": "4.56.2", + "unsloth_version": "2026.1.4", + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file