Upload folder using huggingface_hub (#1)

- 3535051602e7215515920a34b2b88a9899a6623b6f3cb7633e832e9808c1cb4a (e0911cbc6448c12e9104daf6748cd51ab586c19d)
- a0664c76bf69138620f63c2a791325d197bc50540130434b2966ab839b62435d (34e1b89902b509f14d6a3d4684f4939fbd57280f)
- 5b3a493d6b92ce37d303fa5e6c53af2f6df8c158c0c7209f139d7516f3c33760 (6851e3b4adbabdde84d8125c3547572e239df061)
- 10b4ae26f45d6454857fae31622c95bd911e3932b12f9259991a5fdd8e7eccaf (1a84e16d37de5fbb8e9dd299c851173035862c77)
- 8a2482a26a99174f25a3a4c54dfd1d2cf0274869ea103d85c6ee6dd16cadde31 (089cf98e7f52979dc503b5764690ffe720351ba8)
- 537d288b469f898f3d939f809eaaed5c180478feb639eec06210f902a531749a (441ba9eb5d6812b7bbc216e40d927c98e1a78d0a)
- 32d8202e033f201f4f78b6024452b2ed325ec64127566b324e3b9ae3172c6cf9 (44c44b7f5e30bc49fd0550b889d2c4790b6d0390)
- cfbb1783ee56d636113817e8b4a3459dbda11b161bd204c81c85576b363be15f (2e5f9930503d1df15d02f0867a82c1cdc4250fcb)

README.md

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+tags:
+- mlx
+---
+
+# mlx-community/Yi-1.5-34B-8bit
+
+The Model [mlx-community/Yi-1.5-34B-8bit](https://huggingface.co/mlx-community/Yi-1.5-34B-8bit) was converted to MLX format from [01-ai/Yi-1.5-34B](https://huggingface.co/01-ai/Yi-1.5-34B) using mlx-lm version **0.13.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Yi-1.5-34B-8bit")
+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": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "initializer_range": 0.02,
+    "intermediate_size": 20480,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 56,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 5000000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.37.2",
+    "use_cache": true,
+    "vocab_size": 64000
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49460c134e9b3c52086c43df4ac5a271b1ed41dd8d05b4e2b491f0fbe51630e3
+size 5354117230

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1713aca52d0de5a0b28a944c13110c9e5745b03d732f05ce2ce3184ea8e7a48a
+size 5334650055

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aeb5c2dcb14b53ac3ce649709e0cd5985eb5f415d21f5c55379583896758e76
+size 5334650069

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178292b652d9931b45f4308ac1822caac63ef4fb833bbda27c58ccf6ec46e3fc
+size 5334650063

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673549c660f283b271604c23dfd4e34e9b1fabe604507c6e9ac861d87686fc46
+size 5334650069

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3405f77543c732bd1bd6ab406557b3991ad9151f076b38361ddace13ec8577
+size 5334650073

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ccb2c351644ceb2b96e53b4e311e6b51f739b7c7eb59262552276d6987f020
+size 4511829028

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}