Upload folder using huggingface_hub (#1)

- b49b19830c3e6eabe73c9d1ad24bcfb7c42605fb187e5f1c68cd1db12ec37def (52c257b00e629c2cc1563c8d51d931bf570b50b3)
- 872feaf4cc5438fde5e967a7e7181b82bd80609531c0d7d93ba064f7186e5b40 (fc8903c9eeabb199e2806da40e5bb5145c4d4307)
- c3eebcfb6154da588b09006d871db513741f65bd58802458d37e0086c8c51e45 (578dcb7b8f8e0524b490dc162087e875c63f288c)
- add0382ee8ac59fcd38e16d2834c7bb5e0638ca5e258702836be80de2036bb20 (8162d040e71a6711be529d1f4cb77e5182027c6f)
- c815939ea5d5bf475838a60dab19a7750c6203978d41928217eb20e8ed42abe6 (26bf9f50867029540fb4203a91a688ae1d9c36f6)
- bae2499279ff3b5c0f4245da05592fa5dc3ad07e057d3fd7714087bf4f1f2ec0 (908f7f7f0ae2bc8e65f02436329e07f993e0d16f)
- 7e4fcafecd52691a71c67b198742586ed7e2f0f5ec839118c4c6ce91987fa89d (d353f90508eee4f2bd0fa39ec1255f328c952943)
- 1d15e352d7633a70b8c19d1a7924422c09df6b84d93efbe4abd6b6d80c01e4fe (4a42b06142b41988b8557def17e25ba89edd1a92)
- 6b39028b15d1b65e8d86074ae567c1f0f1b4f83545b559d9365583554c1f12b2 (7552902e8aef3627d1fa927c5db1622ac196d30d)
- 3d44b3fa3d910b07e810f497e573e1e26e5b773e8a8148a66ccbaed7721435bf (4ae5def012a70640f39ff00e005df9756e4733ca)
- 64017e9c65220213803a331244a9a06f9548913618c144218dcafe7aafb41276 (bf15603cc188e1f8228bb8344f433e91d49f5229)
- 181ed9751a72824d77f5dce31db78fe51b7edf6c47303b3731e582780bc2f302 (789b74f33fa7ab0b396264ec3d3fdb50396de32f)
- 53b9435a66f135e8e1c282be019c17a987dfe38c4fe417de2faa516163eb6c26 (e6ea3e545ce2df3c4b933f53e6f71419f016d8ba)

README.md

@@ -0,0 +1,26 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- chat
+- mlx
+pipeline_tag: text-generation
+---
+
+# mlx-community/Qwen2-57B-A14B-Instruct-8bit
+
+The Model [mlx-community/Qwen2-57B-A14B-Instruct-8bit](https://huggingface.co/mlx-community/Qwen2-57B-A14B-Instruct-8bit) was converted to MLX format from [Qwen/Qwen2-57B-A14B-Instruct](https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct) using mlx-lm version **0.14.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Qwen2-57B-A14B-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 +1,39 @@
+{
+    "architectures": [
+        "Qwen2MoeForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_moe",
+    "moe_intermediate_size": 2560,
+    "norm_topk_prob": false,
+    "num_attention_heads": 28,
+    "num_experts": 64,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "output_router_logits": false,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 20480,
+    "sliding_window": 65536,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a207246dafd8948d7e8b1ae6a373a5f8b3be851808d2f568145d572d84919b7
+size 4884308032

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacd596b61729d92c9b4b86e0e3fc586b82a32e31b6b3afcd71c90b5c0946926
+size 4898188502

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79d8842981d6c679666f02a978ad4bafee13fd4e8a773dfc0c506e0d550e7d0
+size 4898188506

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a8ad4d3bd0faf530baa32352abd5386870044fdc12223b67eb7e29612e7a42
+size 5163621926

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ff376d2cd635fbad5c17b3ee766422b207ec9fe9dd6905d016238f7e4a4cb4
+size 4898188608

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94a584c9167ceb454f2dcc102c1feaff491b4b3afa07c94f21284f03865a464
+size 4898188619

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd754910c6fa4aee4e8fc493b279c28eca6278818a48acfe71c09c8e9ff74d2
+size 5163622045

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efde7bc39e10cbe3bb7c41be63db20f9e4ef0d60f155109ce78d0bf2bacdd5e
+size 4898188575

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7533b1d1ee3b0a403b741fb1756d6d34c5d1a66e50d86b7942d5c25fcd62eb6
+size 4898188571

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1c5301aa81d77254300dcab80af42c8cb167666ca10a81540930938e4f9105
+size 5163622027

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78fca7206cf59d24a878e2e743ccbaa5e0f7eab48d68a00a9c6ed5c0b7eebefc
+size 4898188591

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e0293cb98b76be88a571eb7430f1a69bb24a673a6d8f2d2c7a63966232389f
+size 4898188561

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244607f0a80608a9c375266a15af8fdf20495fb388396fb4ad9077764072d5d7
+size 1436466320

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": 65536,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}