Commit ·
645ec52
1
Parent(s): a7958bc
Upload folder using huggingface_hub
Browse files- README.md +16 -0
- config.json +82 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- weights.00.safetensors +3 -0
- weights.01.safetensors +3 -0
- weights.02.safetensors +3 -0
- weights.03.safetensors +3 -0
- weights.04.safetensors +3 -0
- weights.05.safetensors +3 -0
- weights.06.safetensors +3 -0
- weights.07.safetensors +3 -0
- weights.08.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
tags:
|
| 4 |
+
- mlx
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# XuanYuan-70B-Chat-mlx
|
| 8 |
+
This model was converted to MLX format from [`Duxiaoman-DI/XuanYuan-70B-Chat`]().
|
| 9 |
+
Refer to the [original model card](https://huggingface.co/Duxiaoman-DI/XuanYuan-70B-Chat) for more details on the model.
|
| 10 |
+
## Use with mlx
|
| 11 |
+
```bash
|
| 12 |
+
pip install mlx
|
| 13 |
+
git clone https://github.com/ml-explore/mlx-examples.git
|
| 14 |
+
cd mlx-examples/llms/hf_llm
|
| 15 |
+
python generate.py --model mlx-community/XuanYuan-70B-Chat-mlx --prompt "My name is"
|
| 16 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 39438,
|
| 3 |
+
"max_position_embeddings": 8192,
|
| 4 |
+
"hidden_size": 8192,
|
| 5 |
+
"intermediate_size": 28672,
|
| 6 |
+
"num_hidden_layers": 80,
|
| 7 |
+
"num_attention_heads": 64,
|
| 8 |
+
"num_key_value_heads": 8,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"rms_norm_eps": 1e-05,
|
| 12 |
+
"pretraining_tp": 1,
|
| 13 |
+
"use_cache": true,
|
| 14 |
+
"rope_theta": 10000.0,
|
| 15 |
+
"rope_scaling": null,
|
| 16 |
+
"attention_bias": false,
|
| 17 |
+
"attention_dropout": 0.0,
|
| 18 |
+
"return_dict": true,
|
| 19 |
+
"output_hidden_states": false,
|
| 20 |
+
"output_attentions": false,
|
| 21 |
+
"torchscript": false,
|
| 22 |
+
"torch_dtype": "float16",
|
| 23 |
+
"use_bfloat16": false,
|
| 24 |
+
"tf_legacy_loss": false,
|
| 25 |
+
"pruned_heads": {},
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"is_encoder_decoder": false,
|
| 28 |
+
"is_decoder": false,
|
| 29 |
+
"cross_attention_hidden_size": null,
|
| 30 |
+
"add_cross_attention": false,
|
| 31 |
+
"tie_encoder_decoder": false,
|
| 32 |
+
"max_length": 20,
|
| 33 |
+
"min_length": 0,
|
| 34 |
+
"do_sample": false,
|
| 35 |
+
"early_stopping": false,
|
| 36 |
+
"num_beams": 1,
|
| 37 |
+
"num_beam_groups": 1,
|
| 38 |
+
"diversity_penalty": 0.0,
|
| 39 |
+
"temperature": 1.0,
|
| 40 |
+
"top_k": 50,
|
| 41 |
+
"top_p": 1.0,
|
| 42 |
+
"typical_p": 1.0,
|
| 43 |
+
"repetition_penalty": 1.0,
|
| 44 |
+
"length_penalty": 1.0,
|
| 45 |
+
"no_repeat_ngram_size": 0,
|
| 46 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 47 |
+
"bad_words_ids": null,
|
| 48 |
+
"num_return_sequences": 1,
|
| 49 |
+
"chunk_size_feed_forward": 0,
|
| 50 |
+
"output_scores": false,
|
| 51 |
+
"return_dict_in_generate": false,
|
| 52 |
+
"forced_bos_token_id": null,
|
| 53 |
+
"forced_eos_token_id": null,
|
| 54 |
+
"remove_invalid_values": false,
|
| 55 |
+
"exponential_decay_length_penalty": null,
|
| 56 |
+
"suppress_tokens": null,
|
| 57 |
+
"begin_suppress_tokens": null,
|
| 58 |
+
"architectures": [
|
| 59 |
+
"LlamaForCausalLM"
|
| 60 |
+
],
|
| 61 |
+
"finetuning_task": null,
|
| 62 |
+
"id2label": {
|
| 63 |
+
"0": "LABEL_0",
|
| 64 |
+
"1": "LABEL_1"
|
| 65 |
+
},
|
| 66 |
+
"label2id": {
|
| 67 |
+
"LABEL_0": 0,
|
| 68 |
+
"LABEL_1": 1
|
| 69 |
+
},
|
| 70 |
+
"tokenizer_class": null,
|
| 71 |
+
"prefix": null,
|
| 72 |
+
"bos_token_id": 1,
|
| 73 |
+
"pad_token_id": 0,
|
| 74 |
+
"eos_token_id": 2,
|
| 75 |
+
"sep_token_id": null,
|
| 76 |
+
"decoder_start_token_id": null,
|
| 77 |
+
"task_specific_params": null,
|
| 78 |
+
"problem_type": null,
|
| 79 |
+
"_name_or_path": "Duxiaoman-DI/XuanYuan-70B-Chat",
|
| 80 |
+
"transformers_version": "4.36.2",
|
| 81 |
+
"model_type": "llama"
|
| 82 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21c5025309cbeced41b89d100d24b0409758d39604bd2d4df63c7b8f85f6d7f3
|
| 3 |
+
size 592204
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": null,
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"spaces_between_special_tokens": false,
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": true
|
| 41 |
+
}
|
weights.00.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb0e7664a55b0756b2cd14e5c40edecad65bc534ee26267a8700c35aaede716d
|
| 3 |
+
size 15871566601
|
weights.01.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5753139e1b78a03c1e7fadb68119f81123b13d9c3b5e2485e389e367b2851c15
|
| 3 |
+
size 15720556353
|
weights.02.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff4c99eb1df0a1cf25d9bf325c18e344b1f22cb36e7e371d180d791f706a78b1
|
| 3 |
+
size 15854789998
|
weights.03.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bc88852ba458713d7f5598bad2bb8f23fdb17a289e8f11e65a61eef170cf169
|
| 3 |
+
size 16031230309
|
weights.04.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:539df9e524020519c6379a0fd569992f7202f6036e0fc60c98f88b96e8beb8ca
|
| 3 |
+
size 15905121266
|
weights.05.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d47f4e747fe2ff0170ac1f47e23665b455855d0af629c070dbfeea10e9c285d8
|
| 3 |
+
size 15804392681
|
weights.06.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:323c09ecd779078d99fb5c28c07abbf08be33bbaec8e3f5e5438ecb97d1672d9
|
| 3 |
+
size 15762695586
|
weights.07.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31b6eb658e9383a5c3e516c770c939d4d127f30260e4aec3aaef8357a5a8872d
|
| 3 |
+
size 15905138475
|
weights.08.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cb2f6691c6fb92031b3397cac16473abe2a4102521262b5a8c7bbd3cca51260
|
| 3 |
+
size 11341617775
|