commit 34c6b328f112a85c1f979ba77bfa2cedc85399ad Author: ModelHub XC Date: Sun May 24 22:50:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlx-community/gemma-3-270m-qat-bf16 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e2b6026 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +*.model 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 +*.safetensors 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_config.json filter=lfs diff=lfs merge=lfs -text +tokenizer.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..e35d9b0 --- /dev/null +++ b/README.md @@ -0,0 +1,36 @@ +--- +license: gemma +tags: +- mlx +library_name: mlx +base_model: google/gemma-3-270m-qat +pipeline_tag: text-generation +--- + +# mlx-community/gemma-3-270m-qat-bf16 + +This model [mlx-community/gemma-3-270m-qat-bf16](https://huggingface.co/mlx-community/gemma-3-270m-qat-bf16) was +converted to MLX format from [google/gemma-3-270m-qat](https://huggingface.co/google/gemma-3-270m-qat) +using mlx-lm version **0.26.3**. + +## Use with mlx + +```bash +pip install mlx-lm +``` + +```python +from mlx_lm import load, generate + +model, tokenizer = load("mlx-community/gemma-3-270m-qat-bf16") + +prompt = "hello" + +if tokenizer.chat_template is not None: + messages = [{"role": "user", "content": prompt}] + prompt = tokenizer.apply_chat_template( + messages, add_generation_prompt=True + ) + +response = generate(model, tokenizer, prompt=prompt, verbose=True) +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..55549c7 --- /dev/null +++ b/config.json @@ -0,0 +1,54 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "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" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0.dev0", + "use_bidirectional_attention": false, + "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..2a395e4 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "cache_implementation": "hybrid", + "do_sample": true, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "4.55.0.dev0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..f5bfd0a --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b34e4a7d7d63804b988fbab3654880b93ddea000376973e1985b7b75e08391 +size 871767174 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..cff5840 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,245 @@ +{ + "metadata": { + "total_size": 871740672, + "total_parameters": 435870336 + }, + "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.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.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..1a61932 --- /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_config.json b/tokenizer_config.json new file mode 100644 index 0000000..341304c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c053f0869e8d4761b783545171059ae290fc93de66aee2d0a2d0bffacac9d77 +size 1155398