Add files using upload-large-folder tool

README.md

@@ -1,3 +1,85 @@
----
-license: mit
----
+---
+license: mit
+library_name: mlx
+pipeline_tag: text-generation
+language:
+- en
+- zh
+tags:
+- code
+- math
+- mlx
+arxiv: 2412.17743
+base_model: yulan-team/YuLan-Mini-Instruct
+model-index:
+- name: YuLan-Mini-Instruct
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: openai_humaneval
+    metrics:
+    - type: pass@10
+      value: 0.866
+      name: pass@10
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: MBPP
+      type: mbpp
+    metrics:
+    - type: pass@10
+      value: 0.857
+      name: pass@10
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: MATH
+      type: math
+    metrics:
+    - type: maj@1
+      value: 0.552
+      name: maj@1
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: gsm8k
+    metrics:
+    - type: maj@1
+      value: 0.717
+      name: maj@1
+      verified: false
+---
+
+# IvanHU/YuLan-Mini-Instruct-4bit
+
+This model [IvanHU/YuLan-Mini-Instruct-4bit](https://huggingface.co/IvanHU/YuLan-Mini-Instruct-4bit) was
+converted to MLX format from [yulan-team/YuLan-Mini-Instruct](https://huggingface.co/yulan-team/YuLan-Mini-Instruct)
+using mlx-lm version **0.22.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("IvanHU/YuLan-Mini-Instruct-4bit")
+
+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 +1,38 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1920,
+    "initializer_range": 5e-05,
+    "intermediate_size": 4800,
+    "max_position_embeddings": 28723,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 30,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 6,
+    "pad_token_id": 102,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 490000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.47.0",
+    "use_cache": false,
+    "vocab_size": 99000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af305e758911190b10538469d3b962594d4c786385b91d965da1d5aec072e724
+size 1364562335

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 +1,86 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    },
+    "102": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<reasoning_step>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"You are YuLan-Mini, created by RUC AI Box. You are a helpful assistant.\" %}\n{%- endif %}\n\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{%- for message in messages %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}