Upload folder using huggingface_hub (#2)

- 56f8543b2c71d8b55eb72e7f49ca79ed66168ed5d57a4c61d47c7b7ffb368a34 (265e271343d12e6ea91687bc4289f99c80dc9a4d)
- 1e777b6d0a3866b8649c4965f964e19355d3236f4f219a9806179c09decf57b1 (856e98fd33bc8d5037ad5108e47b3d40b9657365)
- fff8d637b9a05fd68239019ad1f7de5a488ced18bc04b50928ea8989342c9262 (288a5a78d5d110141e06b6938b582bf05845d450)
- 9d3a84f4cfef1db4077441f2e834cd9c67d1eff57608fb9b46d59db6f8e1cf5e (85ba4bbaf9245eb98f2593d9bd1d7ec00f9fd056)
- fa9c4a1cdbddcc71f55a06d9dd0875007ca4b1042b00378233167f65f3ba43f6 (f946175e30bb5dbc726c1b1eacf5e614990d9e0e)
- ba58a5e52bd694b17076d83daac5dacbb13ea9f9d3a611bd92c049091f48a96f (29ac337a191433c53399b0ba6750891a55117932)
- bccead3119c96a6bfdac72d65de1601d2929d415e3ee6d9dec71bffdd072c1e0 (f159949cdd9c79e759a1035fe1fd766645c9346a)
- 5b387b23ff0e6c05c79fa80c262c4ba79dfe7fab6ccbb5b0a0c2b1dfa329b0f6 (895fdf073a8e8f1bdb09c250a6c2a79fc79000c9)
- f30898dec50e7da72a7640f2836b7637650ed45b77d8459b5e749f4a8451f8a6 (f0148aa397980ce2c25bcaf8b04b95e322cf7a7a)
- d18ad3cffda003fee0c043051e0fc81cde09f644f1881881ef2203499c8fcb94 (c8fbec751cea0ad753ad3bfc6bf555474b325bfb)
- 657bf750c8b757618fcefae24c5871fed8211f96cb30099c47d673f15d78b2e4 (c7bd4bc4dc47f1ae03bd108d3f58d1169d04e96b)
- e4f78974779f85ce70c01f1c5bc70121a027d496c04bb0117fc9b1d95b28281a (54d4e86243a77c74cf5be910aca3cb2c4d411d20)
- 9d7f3cb0457b59f61c01f503c85445694a3cac56ec4734bb8b18fc0ea96d8ad8 (5e3962fbc63ada4b69daf77647c77cbbc7e7337c)
- e1d9d506c90db4742549d22cd20a59b0d17f9eed7116e88771edb93ceb5d9b9c (06012240f07517a3e7bc857b75aa84070c5b0245)
- 53adca4410148b08e9059bf3c4c79c10613d348118372636cc1d68be4c6e0cdd (bbd021c5a52bfa865378c55c676e4a74b0078880)
- 5a3386e045206ce7192724cba373433cd579b4377ce36819115b30aa9e66cd1e (6d63b41c3d632ce2d88826913abaea3ff73f46f0)
- 6c91c822d71843730f95a3b67e6c42181f94edbda81d951d1fb266fed0ed7d77 (7abe719b577803b3b76aa9ac785f4f42f2859550)
- d01312ba1ce4b65559138a9d5407cf4b83da595aeb66223a48d091cc124d34c3 (b9c03cd7a5c3e5e5c95883eacf77f669469cc010)
- 8b42a3656e049a60f5f34225faff1677d9668accfd91359ea6d3b5da54293acf (97b49e494782c59b666e96f9e2f11d0571069c30)
- 6d4933d2274e981d1f66ff1a94368f5e1970a4a8b3cfb21c26e7d022cd9219cb (5d21ccb658d7f49227670a2075c93d556be41bb1)
- 027bc36c2642ac4a94823fc7c76cdf8c7f221f6c3bfd8ad36035ff49cb6c3ce4 (22c211f4d6bc3c79fb194d9e8e83c97618473763)
- 3cf41af27185313003c5d766eb8243ea6d28df9d45ef8660abcc6bbd99f04b36 (7dba77600593d3bc83eb9651653ae7d4815deea2)
- 7642c7375e6b40d726270ea2840af157b62ae2dfd49fa8db049cc9f27fe65773 (1e8e6fd24abd5be5eb6f7626715a6ad458109927)
- ddbb3195aa748099728a2884068a5db6a9e417663ffee13914939b27efc9b962 (df1a713f7bfaa3f178e8ff667cdc7d6d3d6c342e)
- 52c35abd380c9d393fa402fa73e78f8d5085fab523e24b11715bc1a7c3cb8997 (9ad5ff67b132b3a7c4264b91a3cb4d8614ac631c)
- c905b6ec0dc1e812501249aa482f176f1e5a168f00971e1ef8535537dd28e373 (4083c259569d752b69af5bcc138d682c112b0022)
- df7ad5bcf3ff65d203763350628a9c80e3a37becb9580d500e58e865f8b1cad0 (cecd86bfc0ad94dab7144c9486b65a0f0816b6a9)
- 90aa5113723ca732880635260dfa4bf0eed8d48c0f0d7a9638dd8d8d9dca2d93 (80d455f1d52cd925e90e4f1430eeef70115eabd8)
- 15481f468c491ff751a936df3cde2317481003ce2d785c2c7be588054d0c2cd3 (fadb96c7aee541eabd0c3ff8ac08d580bb80b8e7)

README.md

@@ -0,0 +1,33 @@
+---
+license: apache-2.0
+tags:
+- trl
+- orpo
+- generated_from_trainer
+- mlx
+base_model: mistral-community/Mixtral-8x22B-v0.1
+datasets:
+- argilla/distilabel-capybara-dpo-7k-binarized
+inference:
+  parameters:
+    temperature: 0.7
+model-index:
+- name: zephyr-orpo-141b-A35b-v0.1
+  results: []
+---
+
+# mlx-community/zephyr-orpo-141b-A35b-v0.1-8bit
+This model was converted to MLX format from [`HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1`]() using mlx-lm version **0.9.0**.
+Refer to the [original model card](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/zephyr-orpo-141b-A35b-v0.1-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,88 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 65536,
+    "min_length": 0,
+    "model_type": "mixtral",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 48,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_router_logits": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.39.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924875aee1a2064e7e7f44afcbc91120144683818ef09f4002e5074632de74ae
+size 5286637340

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d6ae9bedac5ab39adbc9180fe7b5bd2aee6317b80673ce638f9a6fc48d34b9
+size 5321266592

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1baa60bb50f9d0d16a9e7f1927d91b642e55d51d389301459c3881bf72094fb
+size 5321266588

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1259d6a7c7d47e14df5326b80846e9eb28607ad0879a04df6df2b0c314635cd8
+size 5321266602

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bcc3931706f596f2038f103f8a51e852e4de60c6b5229ae041727db3b7de2f
+size 5321266610

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361a95803a88436ad46477ebb87ed0c44d6449514614a422d648c5006fe55db5
+size 5321266732

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6529474214a716cb211b9f4a2ebb1a95b343f90b754395ea4e59ad50e3d1650e
+size 5321266768

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4539b1c3387d48c04262b2a2f79b2b834c2d1443559997238d8b430b989976
+size 5321266778

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59ab81bde7295d3a3c0ef19a4e0ba11ae73ad75ad1be99324986dc267b1c36e
+size 5321266776

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf51600de760e0b5f1bad25314db92d8972fc716243aa69a092f38c6fd9c6b9
+size 5321266766

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05006737d981cd79b96ad2f97b0892734600082db3db1c671f53a6b66bf40aaf
+size 5321266770

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76aa99b678706a0976b72053db2b7f26bac8103aafe440f93559b399073ac182
+size 5321266754

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98262e24e07ae7f6ac10a575de5c4a4ec4a5417d56863f12e0a85b422aeadc4c
+size 5321266720

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476749b9af1e9c3b9a18b2f334448c78ca718cf9b95aeec4be58e641902f2e79
+size 5321266784

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e561a78a668678c0bdce7f57f7ea5b8b354f486a6e92cd0554a36d79cbeda6
+size 5321266782

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56477be9c5c10562d9de2644472978d1fb5e34fcf8fd4d0b29ba38c5f403f329
+size 5321266766

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f93cabe397382e046be387593ce066f7d8def295e4e304fea6f97cbe225d7b
+size 5321266764

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a219dabd4b71b56d6c320884250f42384c6f62ed092618f0849380e7c41988
+size 5321266778

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2d7ef90ad443ff964553f62e9f386e73d049d20ee3b84ff4220a05a2233bca
+size 5321266772

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb9b333f2bd48ccbfce9781f0f008010e199cde4c5c35a4ba8bf8adeaaca86b
+size 5321266778

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248c5fa48d0e1960381c2c10007f3e5a283cafaef1d9e9615ca3b9c27843310c
+size 5321266750

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b9d4e2251300890fc61a704eb01a7d7fa2981a9027b4e6341f09c4671151a0
+size 5321266764

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7052581166c7622405479bfc7bb26fb38f10ba3054f3e8a00b4da6492f792741
+size 5321266772

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8511e483b219d0ed5d78f8d45a677b21b60b67e9d17febd1bef652588daa9254
+size 5321266754

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7761729798c8a3be63a5abb8dd96d1f417b021c49442eaebcbb3bbecc42204c
+size 5321266772

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a795c5f1f2f83308666ee214035f0069d6e8f70eb7f72c14035ac18693bc6d4c
+size 5321266776

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664df9f59b49478dc3573069b89c9d91f22ec08779f510db11014e028a31a503
+size 5321266774

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b31c40b3b20c2eb3444135dcb803d0cbb9b0f41c1d59d3ea7ec62f3b5a729bc
+size 5321266768

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4022d50e8df7a6fdf7daf5b70af7b7a801d2b5a6d489c445c26e15e8807a49
+size 636754016

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": "</s>",
+    "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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}