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/Qwen1.5-72B-Chat/blob/main/LICENSE
+pipeline_tag: text-generation
+---
+
+# mlx-community/Qwen1.5-72B-Chat-4bit
+This model was converted to MLX format from [`Qwen/Qwen1.5-72B-Chat`]().
+Refer to the [original model card](https://huggingface.co/Qwen/Qwen1.5-72B-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/Qwen1.5-72B-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 +1,86 @@
+{
+    "vocab_size": 152064,
+    "max_position_embeddings": 32768,
+    "hidden_size": 8192,
+    "intermediate_size": 24576,
+    "num_hidden_layers": 80,
+    "num_attention_heads": 64,
+    "use_sliding_window": false,
+    "sliding_window": 32768,
+    "max_window_layers": 70,
+    "num_key_value_heads": 64,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "use_cache": true,
+    "rope_theta": 1000000.0,
+    "attention_dropout": 0.0,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 151643,
+    "pad_token_id": null,
+    "eos_token_id": 151645,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/lei/.cache/huggingface/hub/models--Qwen--Qwen1.5-72B-Chat/snapshots/1a6ccc1215278f962c794b1848c710c29ef4053d",
+    "transformers_version": "4.38.2",
+    "model_type": "qwen2",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec32c6dcbdcc41ae16943c578a62b898142cb59f37d3339420150acbc8e092e0
+size 5340919734

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8019d97e00ba099a61ed8091d9b163e9cb6e151376a48f22448176545ffcf797
+size 5323047676

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fbf62cd220263dd1f0ab5b8b6276db36439c7d139e0a090a8e035ca133c48d
+size 3748969812

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b68a7277f1d7e71cb8588b847bd6d4c47196d7010f08dc989da96004149d67b
+size 5285756358

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f24864158bb9d8e4dde9d3369e5f2dabe40a92b89bfd814d995c437c281ea8
+size 5285756418

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e10e369449f07e728ecf836261e5c89e42a73a37d9c71806dceb390a0c399aa
+size 5361253934

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d648cc1f61914aaedb6038a0d02c4cae3d29ef4a3b5b694acaa0e0d96955713c
+size 5361237436

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3616cbf7ae6c4a8a5ddf9fc2df1e16da55932b067e550cadf9326dafca5fe39f
+size 5361237470

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd958033b2709a6d9422a3c157ac863999483f0ab2449aa6328c6bcd2ae21a19
+size 5361237440

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09d27dfe9f68affb80d0695623660487d8aea170252c473ae99facfb65997b1
+size 5118093777

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e1e45a9cd3ecc85897f03db03b051244eae42729768e4cc0f66c814dca1bb4
+size 5238886672

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']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|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
+}