Add files using upload-large-folder tool

README.md

@@ -0,0 +1,47 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+license: apache-2.0
+library_name: vllm
+inference: false
+extra_gated_description: If you want to learn more about how we process your personal
+  data, please read our <a href="https://www.almawave.com/privacy-policy/">Privacy
+  Policy</a>.
+tags:
+- transformers
+- mlx
+base_model: Almawave/Velvet-14B
+---
+
+# moot20/Velvet-14B-MLX-8bits
+
+The Model [moot20/Velvet-14B-MLX-8bits](https://huggingface.co/moot20/Velvet-14B-MLX-8bits) was
+converted to MLX format from [Almawave/Velvet-14B](https://huggingface.co/Almawave/Velvet-14B)
+using mlx-lm version **0.21.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("moot20/Velvet-14B-MLX-8bits")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,34 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 12544,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 50,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.44.2",
+    "use_cache": false,
+    "vocab_size": 126976
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7d844bf3678d40094e31d62103d008c4d6400a735a70437d2675e72dcc4044
+size 5346738871

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427a80090de98eefcee1536ae903699c57144d3e5f0d8891bdccbb7d51584b77
+size 5324502795

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49571a83c6968668ad655d390e57dd7cc208f490fa6e487934c03c196e29da6
+size 4289663301

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
+  }
+}