Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+---
+language:
+- en
+license: other
+tags:
+- chat
+- mlx
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE
+pipeline_tag: text-generation
+---
+
+# mlx-community/Qwen1.5-110B-Chat-4bit
+This model was converted to MLX format from [`Qwen/Qwen1.5-110B-Chat`]() using mlx-lm version **0.12.0**.
+Refer to the [original model card](https://huggingface.co/Qwen/Qwen1.5-110B-Chat) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Qwen1.5-110B-Chat-4bit")
+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 +1,31 @@
+{
+    "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": 49152,
+    "max_position_embeddings": 32768,
+    "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": 4
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.37.2",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07de56d197686bf0e9bf3167d18ec0beec428e7f2400e0899e4b52b2993882d
+size 5368282084

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5545cb7f8c0414bcab28c69eb069ab86405d4a8e0e22c140a3aadd2d1e09d43e
+size 5355471262

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d351c9406325ec27844fc57fdcbdd35041c259166f054e4880f55478017bbd
+size 5351276819

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca2e4386208be40184a049cb1340b30b7396ac966350dc1d3cd2101de9a2f9f
+size 5351276851

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c3ad63ff08d7e94dc38c81125088454ba3ca2a3040c6c80064ef77336f6a04
+size 5351276863

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7a4bc5a2cce7922d86f565e484840afbc0c145f6ad7f05cd601be3dc294e00
+size 5351276859

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89326ebd0a5c1aa60e1b61f96e8760c9245e42b680b04142dd9ba6b20efe8bc5
+size 5351276843

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a3a511ebb300e2a282213c1e9fcf44a391aef58e0a8b078020edb20c613409
+size 5351276845

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d9e03c3adb5184ebfe4deb60148489e3c7e733941e368b1c3a61c0bfaf3a97
+size 5351276841

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70928aa29e5ffcc5286c08c1b019e8b57d18cabbe73a10d9233896f265127bc
+size 5351276849

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c311f10751d1b6c042e7b23cf7545589178a5be62a5ed6a3dc78ffd10c57db5
+size 5351276827

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2253b0ec8d20d4ea941a709c2b7da9ce279756392684b524a74d8564dca07cbe
+size 3673643280

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
+}