Upload folder using huggingface_hub (#1)

- 7d4b761d5df7391d829952cbb432a704e67e8650086ecf9933a1bded52907f60 (293820769f6e6ef08df75306489b7db5ade4c3e5)
- 62c9a89314fa34658f1794377608c646a3cdee9bd04d95d722878b1e5df21998 (973816ca7f3a2bd557be29f443aa03e242bd4ed1)
- 53beffc7f119b95bb23778203c2ee546ccaeaa8d8e3113ad9a9e33bf650228c8 (2a6395be02b1b6a2b3b6649f2b764503deb8413e)
- 4beb6a999f41ec71d2dc6fda2621d43211fa08b1008c69b83f064465e1e960d1 (d651267b1a6f6d04706be5e995bc56b0a1a7d84c)
- e51c83bb000581ad56cc8361d2e47829afb53a3252872c12f204dab253a86942 (dfd62e5ec02a1f32fd50e64e7c198682c4b9f360)
- bf78fad8c0209a8efeb416d4d2d3bcde34fcef8ca82944803cbd1bea37b1bc11 (66afceaf14fef70642f6a2385b76886b6c32648a)
- f8d48028f06a3cd1801010e8279f3624996228d44b36f0ac38054f2f75fcc833 (b5898f61c9e724b0a2010a76f2a510191ab39abb)
- fc6b8699174288461c53f10751a4ae302f00c867a4088a2ed894b67e5ba86ec2 (61658316326c0dfb187cbb636a46e8e1ba7b0a90)
- c6e0881447758c28f54ccc07855674630c2264f6907b58762bbf24935e231c75 (05d0e5e4fad0b6e8835403826ff4c7f8b5701fea)

README.md

@@ -0,0 +1,32 @@
+---
+base_model: rAIfle/SorcererLM-8x22b-bf16
+license: apache-2.0
+tags:
+- mlx
+---
+
+# mlx-community/SorcererLM-8x22b-2bit
+
+The Model [mlx-community/SorcererLM-8x22b-2bit](https://huggingface.co/mlx-community/SorcererLM-8x22b-2bit) was converted to MLX format from [rAIfle/SorcererLM-8x22b-bf16](https://huggingface.co/rAIfle/SorcererLM-8x22b-bf16) using mlx-lm version **0.19.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/SorcererLM-8x22b-2bit")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 65536,
+    "model_type": "mixtral",
+    "num_attention_heads": 48,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "quantization": {
+        "group_size": 64,
+        "bits": 2
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 2
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.45.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32000
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a1613a50a9b07af92d03c72a045e8dac002d091e317517c47bae46c028b9ae
+size 5287557546

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e56d0d3be382ef179b50436cccca8709ea950a3bbf353dc6e7c1526d34be4f
+size 5226142180

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885fdfdd5ecb465b9c17a1be7fe60dce02bce2b37f4ac3e02ad8364aa52f2987
+size 5226142195

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983e3a973a59632072f3d62821114bed46ac07ba770160de1fc5cedc526792fe
+size 5198575166

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f31948ca12a1947c7a3feaa34d04e62870d69435a1ad48cc7dfc6765589fce0
+size 5226142247

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efc4a8a98b52a9a0853d8552ed5b47848f81c1d1b98041eed346a6c2c14157b0
+size 5226142201

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988eef7ea4b223424f71937fe28398217c11e18b16a06e6aa624f0425db5a691
+size 5198575226

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7771c46dc10da2990ab58f5f6108d748b56d9be7313661d529efabf642b8f19e
+size 5226142263

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfd8cdbddd12a3d4525d38cdfe5cb35b4f4e1df804f686b427b7dcd86799010
+size 2129880719

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{{ messages[0]['content'].strip() }}{% else %}{% set loop_messages = messages %}{{ 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions.' }}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ ' USER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% else %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ '\nUSER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ASSISTANT:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}