Upload folder using huggingface_hub (#1)

- bfbe11ca15d9fb713780aac5245f5d5509227ca2b94188bcb1aa6c835c3af9eb (2cf06fad10a01bf59d9345a5e8e34365f4e40307)
- 7bab8d94898c9b22c5aa77143aa7fed2a584e9efc3bac7c86aae59ae8cd2c49a (8134183a299f7ecc654c9e213f39cc337328ec4b)
- 5ca61a6200f6ef86477b6fe1f45e852ef094aab6faaac702bed59249457fa2df (3041f18d0da8f8f5525049d1d6f01fd6c48cfd71)
- 9f78dbc3144d3ee6f41f7ac0d0d22a2bcbeb28b5e9f7cfac90f3c2da191c7600 (e754abc6592745b0d0921e5a94f680c941381801)
- 47730bef7623c762fb31498b0b9e343f6e524c1473f6cc4d3c8fdb14d5e7f411 (726a94f01aaa9540d54823e334e8cf85eb60851e)

README.md

@@ -0,0 +1,102 @@
+---
+license: apache-2.0
+library_name: transformers
+tags:
+- code
+- granite
+- mlx
+base_model: ibm-granite/granite-34b-code-base
+datasets:
+- bigcode/commitpackft
+- TIGER-Lab/MathInstruct
+- meta-math/MetaMathQA
+- glaiveai/glaive-code-assistant-v3
+- glaive-function-calling-v2
+- bugdaryan/sql-create-context-instruction
+- garage-bAInd/Open-Platypus
+- nvidia/HelpSteer
+metrics:
+- code_eval
+pipeline_tag: text-generation
+inference: true
+model-index:
+- name: granite-34b-code-instruct
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 62.2
+      name: pass@1
+    - type: pass@1
+      value: 56.7
+      name: pass@1
+    - type: pass@1
+      value: 62.8
+      name: pass@1
+    - type: pass@1
+      value: 47.6
+      name: pass@1
+    - type: pass@1
+      value: 57.9
+      name: pass@1
+    - type: pass@1
+      value: 41.5
+      name: pass@1
+    - type: pass@1
+      value: 53.0
+      name: pass@1
+    - type: pass@1
+      value: 45.1
+      name: pass@1
+    - type: pass@1
+      value: 50.6
+      name: pass@1
+    - type: pass@1
+      value: 36.0
+      name: pass@1
+    - type: pass@1
+      value: 42.7
+      name: pass@1
+    - type: pass@1
+      value: 23.8
+      name: pass@1
+    - type: pass@1
+      value: 54.9
+      name: pass@1
+    - type: pass@1
+      value: 47.6
+      name: pass@1
+    - type: pass@1
+      value: 55.5
+      name: pass@1
+    - type: pass@1
+      value: 51.2
+      name: pass@1
+    - type: pass@1
+      value: 47.0
+      name: pass@1
+    - type: pass@1
+      value: 45.1
+      name: pass@1
+---
+
+# mlx-community/granite-34b-code-instruct-4bit
+
+The Model [mlx-community/granite-34b-code-instruct-4bit](https://huggingface.co/mlx-community/granite-34b-code-instruct-4bit) was converted to MLX format from [ibm-granite/granite-34b-code-instruct](https://huggingface.co/ibm-granite/granite-34b-code-instruct) 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/granite-34b-code-instruct-4bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,32 @@
+{
+    "activation_function": "gelu_pytorch_tanh",
+    "architectures": [
+        "GPTBigCodeForCausalLM"
+    ],
+    "attention_softmax_in_fp32": true,
+    "attn_pdrop": 0.1,
+    "bos_token_id": 0,
+    "embd_pdrop": 0.1,
+    "eos_token_id": 0,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "gpt_bigcode",
+    "multi_query": true,
+    "n_embd": 6144,
+    "n_head": 48,
+    "n_inner": 24576,
+    "n_layer": 88,
+    "n_positions": 8192,
+    "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "resid_pdrop": 0.1,
+    "scale_attention_softmax_in_fp32": true,
+    "scale_attn_weights": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.41.0.dev0",
+    "use_cache": true,
+    "vocab_size": 49152
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432ada8fab674df9576108bce3e3cdc5acc40256e27c1920fe13c3b2e278fa9d
+size 5362180081

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0bbb6a4086dbf36566ed21aba7c3238ca93c5f0144f2efd3b207d9191760ae7
+size 5333980027

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07501758b13c75a9e05daaa65b244afdcf54bae30f14a55e70c291531562b2fa
+size 5333980031

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6c1b9369756a00964c4542cf8f7c6a7eb941ca3b7de0477084feb30dbb4860
+size 2943675388

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'Question:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'system' %}\n{{ 'System:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Answer:\n'  + message['content'] + '\n\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Answer:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}