Upload folder using huggingface_hub (#1)

- 1d853784a0dace70bce32f8b6ba1761faac04b59c3d7b3224112d2cc1d0e204c (1038d300a71ffe8d725da53ca9a2c1fb01276a82)
- c0de02df36028150c79b00b9e6d4f482bbcc863d16e43fca69090be63b2c9ed5 (7f317d02107e58c3c0df42cf426e7007cb09c3a8)
- 60444ca22fd9ca80461b18993cf70b963d9d19ebe1309c300ca29ca11501b1c4 (ad0cd98fccfbe4dbccef932f4684a468a3e4b5f2)
- 0766463862bb667d22b1bf1306cd7e5c56169fc2fad29ef6fa1e51b81b61577e (2844df19a2f30dd77f0379bfa6263a9f83aea050)
- 3de07fea0969984894177a37ff5506395ce50aa027487a5980ec945e27a5147d (9aa1d3d7a7a9a7a87cd316aa242fab1e4910619f)

README.md

@@ -0,0 +1,35 @@
+---
+license: other
+tags:
+- generated_from_trainer
+- axolotl
+- mlx
+base_model: Qwen/Qwen2-72B
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- microsoft/orca-math-word-problems-200k
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen1.5-110B/blob/main/LICENSE
+---
+
+# mlx-community/dolphin-2.9.2-qwen2-72b-2bit
+This model was converted to MLX format from [`cognitivecomputations/dolphin-2.9.2-qwen2-72b`]() using mlx-lm version **0.12.1**.
+Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-72b) 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/dolphin-2.9.2-qwen2-72b-2bit")
+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 +1,30 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 29568,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": "2"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.2",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497a60ab69b445f21d1c36c16eaeb7201bc43d509ae2ca06ced756dcde5444ee
+size 5353358760

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6341332d0aecb78ec60ee65e85611ef8dfa53d7fd59c46ada2946d1f69a33496
+size 5308829289

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c768f586425678db39feebf26ccea5e0cd356e5d6385bfe206cc0b8477a340a
+size 5363584842

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ff2a6584b1d7c34ffb86cf5d549e2966a37c617d23b16507e6469a2b5b3249
+size 5335065549

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c019b7822f55f559af027774158729d596433de397d306cf76366bb96c8c9d4
+size 1363695467

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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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
+}