8c4956c7ba83076a372e638e7687f0b052984113fedd2819bb17fad5e40f26d2

README.md

@@ -0,0 +1,47 @@
+---
+license: other
+license_name: mrl
+language:
+- en
+tags:
+- chat
+- mlx
+pipeline_tag: text-generation
+library_name: transformers
+datasets:
+- anthracite-org/c2_logs_16k_mistral-large_v1.2
+- anthracite-org/kalo-opus-instruct-22k-no-refusal
+- lodrick-the-lafted/kalo-opus-instruct-3k-filtered
+- anthracite-org/nopm_claude_writing_fixed
+- anthracite-org/kalo_opus_misc_240827
+- anthracite-org/kalo_misc_part2
+base_model: anthracite-org/magnum-v4-123b
+---
+
+# mlx-community/magnum-v4-123b-4bit
+
+The Model [mlx-community/magnum-v4-123b-4bit](https://huggingface.co/mlx-community/magnum-v4-123b-4bit) was
+converted to MLX format from [anthracite-org/magnum-v4-123b](https://huggingface.co/anthracite-org/magnum-v4-123b)
+using mlx-lm version **0.20.4**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/magnum-v4-123b-4bit")
+
+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": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.45.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32768
+}

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d3bf58940ceeca88ced1b1b63bd3b2046b018cdbbd75fa8a41c6bd5a777a4f
+size 226492716

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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