3586c445893aa2b117c3cb1c6290d723d15095ccd1ef6c29278935a014fbf978

README.md

@@ -0,0 +1,34 @@
+---
+base_model: FluffyKaeloky/Luminum-v0.1-123B
+library_name: transformers
+tags:
+- mergekit
+- merge
+- mlx
+---
+
+# shanginn/Luminum-v0.1-123B-mlx-quantized-2bit
+
+The Model [shanginn/Luminum-v0.1-123B-mlx-quantized-2bit](https://huggingface.co/shanginn/Luminum-v0.1-123B-mlx-quantized-2bit) was converted to MLX format from [FluffyKaeloky/Luminum-v0.1-123B](https://huggingface.co/FluffyKaeloky/Luminum-v0.1-123B) using mlx-lm version **0.19.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("shanginn/Luminum-v0.1-123B-mlx-quantized-2bit")
+
+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)
+```

config.json

@@ -0,0 +1,34 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 2
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 2
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.44.2",
+    "use_cache": true,
+    "vocab_size": 32768
+}

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f35ec5322d769b79081f3c7d9f8fa58b152b8ec50ec73cc0523d650bb9b0e8
+size 935981527

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583