Upload folder using huggingface_hub

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- ja
+- en
+license: mit
+library_name: transformers
+tags:
+- mlx
+---
+
+# mlx-community/stockmark-100b-4bit
+This model was converted to MLX format from [`stockmark/stockmark-100b`]() using mlx-lm version **0.12.1**.
+Refer to the [original model card](https://huggingface.co/stockmark/stockmark-100b) 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/stockmark-100b-4bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,32 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "hidden_act": "silu",
+    "hidden_size": 9216,
+    "initializer_range": 0.02,
+    "intermediate_size": 32256,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 72,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
+    "pad_token_id": 2,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.1",
+    "use_cache": true,
+    "vocab_size": 60416
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544a380e8575c4af6988bac63dcbc03e5eb31153f08d30cd9fff912d70549c20
+size 5282191464

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f96765d78569a7b3b3d10a6182d9218f67bf85d1b0c3ce91a1d42d625bd760
+size 5364508499

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e70a9487c241519376aa2d58392286741d47304a62a8419393fd96b6ee19632
+size 5303425697

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4909577a6400c11cca7a94f377ac7d0614e7032cf0d51dbc92c7355cd412ab4b
+size 5303462745

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906fc7476f3a26d013a0d0c268c95449bda8601d19d1b2c0d55af2cc7358844b
+size 5303462788

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb8593b0ad813338361987f6d408b02d91893b4e48673e2b91d255c28563851
+size 5364508495

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e213cf9ead59c3075b1655abb284ec4b73c78e5b80a781961ab6325dd89bc397
+size 5303425679

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2be70436d95fed7066e514bd040499f63408c3d50a810aceb28a560a473dd4a
+size 5303462797

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ae214af66295974e2c00578794fe18a746e1c115421227609f4946cc2963b0
+size 5303462720

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60d3730ecebc8355c104848b44e137dd45faf8f67aaa1c2e33d821205761e45
+size 5364508535

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e7f9f7685d8130ea671921df6fd5da3efea2dd6c0c6e23a795c722ed501523
+size 921068451

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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}