Initial commit

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,93 @@
+---
+license: other
+license_name: apache-2.0
+language:
+- en
+base_model: louisbrulenaudet/Maxine-34B-stock
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- microsoft/orca-math-word-problems-200k
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
+library_name: transformers
+tags:
+- mlx
+- merge
+- mergekit
+- louisbrulenaudet/Maxine-34B-stock
+- ConvexAI/Luminex-34B-v0.2
+- fblgit/UNA-34BeagleSimpleMath-32K-v1
+- chemistry
+- biology
+- math
+pipeline_tag: text-generation
+model-index:
+- name: Maxine-34B-stock
+  results:
+  - task:
+      type: text-generation
+    metrics:
+    - name: Average
+      type: Average
+      value: 77.28
+    - name: ARC
+      type: ARC
+      value: 74.06
+    - name: GSM8K
+      type: GSM8K
+      value: 72.18
+    - name: Winogrande
+      type: Winogrande
+      value: 83.9
+    - name: TruthfulQA
+      type: TruthfulQA
+      value: 70.18
+    - name: HellaSwag
+      type: HellaSwag
+      value: 86.74
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+---
+
+<center><img src='https://i.imgur.com/dU9dUh0.png' width='500px'></center>
+
+# mlx-community/Maxine-34B-stock
+
+This model was converted to MLX format from [`louisbrulenaudet/Maxine-34B-stock`]() using mlx-vlm version **0.15.2**.
+Refer to the [original model card](louisbrulenaudet/Maxine-34B-stock) for more details on the model.
+
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+python -m mlx_vlm.generate --model  mlx-community/Maxine-34B-stock --max-tokens 100 --temp 0.0
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Maxine-34B-stock")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```
+
+## Citing & Authors
+
+If you use this code in your research, please use the following BibTeX entry.
+
+```BibTeX
+@misc{louisbrulenaudet2024,
+  author =       {Louis Brulé Naudet},
+  title =        {Maxine-34B-stock, an xtraordinary 34B model},
+  year =         {2024}
+  howpublished = {\url{https://huggingface.co/mlx-community/Maxine-34B-stock}},
+}
+```
+
+## Feedback
+
+If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com).

README.md

@@ -0,0 +1,92 @@
+---
+license_name: apache-2.0
+language:
+- en
+base_model: louisbrulenaudet/Maxine-34B-stock
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- microsoft/orca-math-word-problems-200k
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
+library_name: transformers
+tags:
+- mlx
+- merge
+- mergekit
+- louisbrulenaudet/Maxine-34B-stock
+- ConvexAI/Luminex-34B-v0.2
+- fblgit/UNA-34BeagleSimpleMath-32K-v1
+- chemistry
+- biology
+- math
+pipeline_tag: text-generation
+model-index:
+- name: Maxine-34B-stock
+  results:
+  - task:
+      type: text-generation
+    metrics:
+    - name: Average
+      type: Average
+      value: 77.28
+    - name: ARC
+      type: ARC
+      value: 74.06
+    - name: GSM8K
+      type: GSM8K
+      value: 72.18
+    - name: Winogrande
+      type: Winogrande
+      value: 83.9
+    - name: TruthfulQA
+      type: TruthfulQA
+      value: 70.18
+    - name: HellaSwag
+      type: HellaSwag
+      value: 86.74
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+---
+
+<center><img src='https://i.imgur.com/dU9dUh0.png' width='500px'></center>
+
+# mlx-community/Maxine-34B-stock
+
+This model was converted to MLX format from [`louisbrulenaudet/Maxine-34B-stock`]() using mlx-vlm version **0.15.2**.
+Refer to the [original model card](louisbrulenaudet/Maxine-34B-stock) for more details on the model.
+
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+python -m mlx_vlm.generate --model  mlx-community/Maxine-34B-stock --max-tokens 100 --temp 0.0
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Maxine-34B-stock")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```
+
+## Citing & Authors
+
+If you use this code in your research, please use the following BibTeX entry.
+
+```BibTeX
+@misc{louisbrulenaudet2024,
+  author =       {Louis Brulé Naudet},
+  title =        {Maxine-34B-stock, an xtraordinary 34B model},
+  year =         {2024}
+  howpublished = {\url{https://huggingface.co/mlx-community/Maxine-34B-stock}},
+}
+```
+
+## Feedback
+
+If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com).

config.json

@@ -0,0 +1,87 @@
+{
+    "vocab_size": 64000,
+    "max_position_embeddings": 200000,
+    "hidden_size": 7168,
+    "intermediate_size": 20480,
+    "num_hidden_layers": 60,
+    "num_attention_heads": 56,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 5000000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "mlp_bias": false,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 1,
+    "pad_token_id": 0,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/home/jupyter/.cache/huggingface/hub/models--louisbrulenaudet--Maxine-34B-stock/snapshots/11ab34e48d24d3a1105280433b09edc0665db09a",
+    "transformers_version": "4.42.3",
+    "model_type": "llama",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

gitattributes.txt

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e4c17389c3bc0e9a2b8e09e505849e5cb7f46510908c4c7be1340deca96a09
+size 5348111224

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05eb39bfe65294ef2e8af793e77f7d665ba07ec30fba33cdfccb58995d321ea
+size 5363802119

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3c93f85e1d55b7bbf3b5f51341945d9536d318ad8be5c9080948334f9f0b2c
+size 5334900413

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b69ea3bd3d55031f9195b9c1bc55f0205ef106d16ff49ca90be76fb144d2a3
+size 3957813114

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": "<unk>",
+    "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 +1,44 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}