初始化项目，由ModelHub XC社区提供模型

Model: YoAbriel/KodaLite-1.3B-mlx
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,54 @@
+---
+language: en
+license: apache-2.0
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+  - text-generation
+  - mlx
+  - apple-silicon
+base_model: YoAbriel/KodaLite-1.3B
+---
+
+# KodaLite-1.3B — MLX (fp16)
+
+MLX version of [YoAbriel/KodaLite-1.3B](https://huggingface.co/YoAbriel/KodaLite-1.3B), optimized for Apple Silicon (M1/M2/M3/M4).
+
+**Size**: ~2.5 GB | **Precision**: bfloat16
+
+## Usage
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tok = load("YoAbriel/KodaLite-1.3B-mlx")
+prompt = tok.apply_chat_template(
+    [{"role": "user", "content": "What is the capital of France?"}],
+    tokenize=False,
+    add_generation_prompt=True,
+)
+print(generate(model, tok, prompt=prompt, max_tokens=80))
+```
+
+Or from the command line:
+
+```bash
+mlx_lm.generate --model YoAbriel/KodaLite-1.3B-mlx \
+  --prompt "<|user|>\nHello\n<|assistant|>\n" --max-tokens 80
+```
+
+## Other quantizations
+
+- [YoAbriel/KodaLite-1.3B-mlx-8bit](https://huggingface.co/YoAbriel/KodaLite-1.3B-mlx-8bit) — 1.4 GB, 8-bit
+
+## Limitations
+
+Small model (1.27B params), undertrained (1.64B tokens). See the [base model card](https://huggingface.co/YoAbriel/KodaLite-1.3B) for full details.
+
+## License
+
+Apache 2.0

chat_template.jinja

@@ -0,0 +1,5 @@
+{% for m in messages %}{% if m['role'] == 'user' %}<|user|>
+{{ m['content'] }}
+<|assistant|>
+{% elif m['role'] == 'assistant' %}{{ m['content'] }}
+<|end|>{% endif %}{% endfor %}

config.json

@@ -0,0 +1,25 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 5504,
+    "max_position_embeddings": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 8,
+    "pad_token_id": 50256,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.46.0",
+    "use_cache": true,
+    "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "do_sample": true,
+  "temperature": 0.7,
+  "top_k": 40,
+  "max_new_tokens": 150,
+  "transformers_version": "4.46.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9de44a50960a04d87c52b0bd4155787a2c1cac1e57ed3682aaf841917af12c
+size 2538443079

model.safetensors.index.json

@@ -0,0 +1,227 @@
+{
+    "metadata": {
+        "total_size": 2538418176,
+        "total_parameters": 1269209088
+    },
+    "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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"
+    }
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}