Upload folder using huggingface_hub (#1)

- b1f46581c7ea7a70734dc9f12ec1d996cc905c3b0206f3ff17730af3619a4a35 (4bb23ed954d51b788f5720fac3f0b9b1b5da8569)
- bff13ef997e250584362f7055527acaca556edaa5dd6d933e5b2e8e2fca39673 (d32103c22a16ae7f46311a846f277fc9852003de)
- e717b3aa6b843c5257e1a2a57ae1d08125bacda36ae2cea9f894d86b9765db4a (b80a4560f77212e2b14e49b923230e49335e049a)
- 5165459357654485a0e30f18bd46533734372c458a9b78ca264aa3fd75b61a33 (5d3b3df12f8f8a66549190cc33a422f96b890b28)
- 2680b6ebef22e255ac7b5e6c140cd654550ac67e89fa53f4b3b2eaa278a5b6da (2cc6b8f599e96d0ffc2461e17ff80580ca5cbc73)

README.md

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+tags:
+- mlx
+---
+
+# mlx-community/Yi-1.5-34B-Chat-4bit
+
+The Model [mlx-community/Yi-1.5-34B-Chat-4bit](https://huggingface.co/mlx-community/Yi-1.5-34B-Chat-4bit) was converted to MLX format from [01-ai/Yi-1.5-34B-Chat](https://huggingface.co/01-ai/Yi-1.5-34B-Chat) 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-Chat-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": 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": 4
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 5000000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.0",
+    "use_cache": false,
+    "vocab_size": 64000
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c7cefa509fb7df206db262b5b60b86c20a600a26ff8f93bd265df289e1bf4f
+size 5345192455

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940dbbe9cfca30a9bb8f2ed0c6da7b33efa0b533231b191d77deade78243faeb
+size 5334900439

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634ab2b1ebd3e4af20f631bc73992620c9bc42d752dbe362f94a5e380ad60565
+size 5334900447

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6f06c020188c2733af2c0602f1484eefdafa3bb068087fdc249e19c25a2b5a
+size 3330177746

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,53 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}