commit f4a071b5aeb829a0269894b19313cf842c3324f2 Author: ModelHub XC Date: Fri May 22 05:44:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: codelion/gemma-3-1b-it-ICM-DPO-mlx-fp16 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..65587e6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 + +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer_config.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..1919a39 --- /dev/null +++ b/README.md @@ -0,0 +1,39 @@ +--- +base_model: codelion/gemma-3-1b-it-ICM-DPO +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3_text +- mlx +- mlx-my-repo +license: apache-2.0 +language: +- en +--- + +# codelion/gemma-3-1b-it-ICM-DPO-mlx-fp16 + +The Model [codelion/gemma-3-1b-it-ICM-DPO-mlx-fp16](https://huggingface.co/codelion/gemma-3-1b-it-ICM-DPO-mlx-fp16) was converted to MLX format from [codelion/gemma-3-1b-it-ICM-DPO](https://huggingface.co/codelion/gemma-3-1b-it-ICM-DPO) using mlx-lm version **0.25.3**. + +## Use with mlx + +```bash +pip install mlx-lm +``` + +```python +from mlx_lm import load, generate + +model, tokenizer = load("codelion/gemma-3-1b-it-ICM-DPO-mlx-fp16") + +prompt="hello" + +if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: + messages = [{"role": "user", "content": prompt}] + prompt = tokenizer.apply_chat_template( + messages, tokenize=False, add_generation_prompt=True + ) + +response = generate(model, tokenizer, prompt=prompt, verbose=True) +``` diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e17bde0 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "": 262144 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1117055 --- /dev/null +++ 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 -%} + {{ '' + 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' -%} + {{ '' }} + {%- elif item['type'] == 'text' -%} + {{ item['text'] | trim }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ raise_exception("Invalid content type") }} + {%- endif -%} + {{ ' +' }} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{'model +'}} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..cf6fa4d --- /dev/null +++ b/config.json @@ -0,0 +1,64 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 106, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 1152, + "initializer_range": 0.02, + "intermediate_size": 6912, + "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" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 26, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": 512, + "torch_dtype": "float16", + "transformers_version": "4.53.2", + "unsloth_fixed": true, + "unsloth_version": "2025.7.3", + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9a4ad8f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1, + 106 + ], + "max_length": 32768, + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "4.53.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..5dbea07 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb2fe410cccac69536b4d33020106b66f50d2d29f7b6c5e37c06683bc9884082 +size 2603790719 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b0a4bf7 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,349 @@ +{ + "metadata": { + "total_size": 2603751680, + "total_parameters": 1301875840 + }, + "weight_map": { + "lm_head.weight": "model.safetensors", + "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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..bdd437b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "boi_token": "", + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eoi_token": "", + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "image_token": "", + "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..29401f9 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795 +size 33384568 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..14f810a --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c +size 4689074 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6251e3d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793a65ae6b834678f7161656e1322c6afe71d7ba5c6e40566e9b2312101a214d +size 1155396