Upload folder using huggingface_hub

README.md

@@ -0,0 +1,28 @@
+---
+language:
+- en
+license: other
+tags:
+- chat
+- mlx
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2-Math-72B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
+---
+
+# mlx-community/Qwen2-Math-72B-Instruct-8bit
+
+The Model [mlx-community/Qwen2-Math-72B-Instruct-8bit](https://huggingface.co/mlx-community/Qwen2-Math-72B-Instruct-8bit) was converted to MLX format from [Qwen/Qwen2-Math-72B-Instruct](https://huggingface.co/Qwen/Qwen2-Math-72B-Instruct) using mlx-lm version **0.16.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Qwen2-Math-72B-Instruct-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,32 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 29568,
+    "max_position_embeddings": 4096,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.1",
+    "use_cache": true,
+    "use_mrope": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b233c262df637f24b4b1ca5fc90382d47a919df9172ed6ffd28da6e8dc79cd4
+size 5214291418

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93971bd6d4f335e798dac79fe2a4432791faddcb6bf74b5ee19a68399b46c84d
+size 5177560124

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9bcf4d81280774361320bcfc834c402bf0ded2c778ace461dd6973299231e75
+size 5338047575

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e20ff6ea021cd2b4e81492f27580edb9f2188a0dcd7949d00e0b8a3ea28748
+size 5338047581

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d78016b620d67dfbd13dd9d039a6cacef1620676d57368751786444df383509
+size 5177560270

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006642406c4cba51a902649069da4ce746e56eb02520494bc5e92b75742c4dd1
+size 5338047562

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234529ca9ea410777f50af20aefa6171ed824fe46518da9fb4d35835e227ea01
+size 5338047557

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:470fc497fbe3fa8e3492ddae721d07be71873b5d7559b75fb7f4331b75782454
+size 5177560278

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84264319b81c5c8ba5bf12675e9d6a695f4fb54f69d4fe0f819482c61ced9637
+size 5338047594

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9860f1e0f5bf86ef8219580afd8e986ae267e158bea3f2c3eed95a3fbaf2b16a
+size 5338047549

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9547e2242539c0c94a774b5f57b51f099d1b212dc0532fff57eaca09a008009e
+size 5177560280

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef21479e8a3508fa7e9407feeac9b257055cf60e24edb4190902dd538fa215fe
+size 5338047560

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b266dd16570d66b074d3448bcd4951932d4de603b382fe2ec29f8a396cdb4d1
+size 5338047535

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6057ee1890acbde41f0a98e1dc2831af7cc34895264e65a9b8ad1aa6035843e5
+size 5177560290

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d45d088407ee4afb073148499654c3317bc2ca6957970b3bc731bed599c984d
+size 3446110912

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}