rohith.bheemreddy commited on
Commit
29cf0e6
·
1 Parent(s): aedae5e

Files as per mlx V3 repo

Browse files
README.md CHANGED
@@ -1,14 +1,14 @@
1
  ---
2
- base_model: deepseek-ai/DeepSeek-R1
3
  tags:
4
  - mlx
5
  ---
6
 
7
- # mlx-community/DeepSeek-R1-4bit
8
 
9
- The Model [mlx-community/DeepSeek-R1-4bit](https://huggingface.co/mlx-community/DeepSeek-R1-4bit) was
10
- converted to MLX format from [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)
11
- using mlx-lm version **0.21.0**.
12
 
13
  ## Use with mlx
14
 
@@ -19,7 +19,7 @@ pip install mlx-lm
19
  ```python
20
  from mlx_lm import load, generate
21
 
22
- model, tokenizer = load("mlx-community/DeepSeek-R1-4bit")
23
 
24
  prompt = "hello"
25
 
 
1
  ---
2
+ base_model: deepseek-ai/DeepSeek-V3
3
  tags:
4
  - mlx
5
  ---
6
 
7
+ # mlx-community/DeepSeek-V3-4bit
8
 
9
+ The Model [mlx-community/DeepSeek-V3-4bit](https://huggingface.co/mlx-community/DeepSeek-V3-4bit) was
10
+ converted to MLX format from [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3)
11
+ using mlx-lm version **0.20.4**.
12
 
13
  ## Use with mlx
14
 
 
19
  ```python
20
  from mlx_lm import load, generate
21
 
22
+ model, tokenizer = load("mlx-community/DeepSeek-V3-4bit")
23
 
24
  prompt = "hello"
25
 
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 419539258368
4
  },
5
  "weight_map": {
6
  "lm_head.biases": "model-00088-of-00088.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 377606822912
4
  },
5
  "weight_map": {
6
  "lm_head.biases": "model-00088-of-00088.safetensors",
tokenizer.json CHANGED
@@ -7214,21 +7214,21 @@
7214
  },
7215
  {
7216
  "id": 128798,
7217
- "content": "<think>",
7218
  "single_word": false,
7219
  "lstrip": false,
7220
  "rstrip": false,
7221
- "normalized": true,
7222
- "special": false
7223
  },
7224
  {
7225
  "id": 128799,
7226
- "content": "</think>",
7227
  "single_word": false,
7228
  "lstrip": false,
7229
  "rstrip": false,
7230
- "normalized": true,
7231
- "special": false
7232
  },
7233
  {
7234
  "id": 128800,
 
7214
  },
7215
  {
7216
  "id": 128798,
7217
+ "content": "<|place▁holder▁no▁798|>",
7218
  "single_word": false,
7219
  "lstrip": false,
7220
  "rstrip": false,
7221
+ "normalized": false,
7222
+ "special": true
7223
  },
7224
  {
7225
  "id": 128799,
7226
+ "content": "<|place▁holder▁no▁799|>",
7227
  "single_word": false,
7228
  "lstrip": false,
7229
  "rstrip": false,
7230
+ "normalized": false,
7231
+ "special": true
7232
  },
7233
  {
7234
  "id": 128800,
tokenizer_config.json CHANGED
@@ -6412,20 +6412,20 @@
6412
  "special": true
6413
  },
6414
  "128798": {
6415
- "content": "<think>",
6416
  "lstrip": false,
6417
- "normalized": true,
6418
  "rstrip": false,
6419
  "single_word": false,
6420
- "special": false
6421
  },
6422
  "128799": {
6423
- "content": "</think>",
6424
  "lstrip": false,
6425
- "normalized": true,
6426
  "rstrip": false,
6427
  "single_word": false,
6428
- "special": false
6429
  },
6430
  "128800": {
6431
  "content": "<|fim▁hole|>",
@@ -6549,12 +6549,12 @@
6549
  }
6550
  },
6551
  "bos_token": "<|begin▁of▁sentence|>",
6552
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\\n\\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' in message %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- else %}{{'<|Assistant|>' + message['content'] + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- endfor %}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' not in message %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}",
6553
  "clean_up_tokenization_spaces": false,
6554
  "eos_token": "<|end▁of▁sentence|>",
6555
  "extra_special_tokens": {},
6556
  "legacy": true,
6557
- "model_max_length": 16384,
6558
  "pad_token": "<|end▁of▁sentence|>",
6559
  "sp_model_kwargs": {},
6560
  "tokenizer_class": "LlamaTokenizer",
 
6412
  "special": true
6413
  },
6414
  "128798": {
6415
+ "content": "<|place▁holder▁no▁798|>",
6416
  "lstrip": false,
6417
+ "normalized": false,
6418
  "rstrip": false,
6419
  "single_word": false,
6420
+ "special": true
6421
  },
6422
  "128799": {
6423
+ "content": "<|place▁holder▁no▁799|>",
6424
  "lstrip": false,
6425
+ "normalized": false,
6426
  "rstrip": false,
6427
  "single_word": false,
6428
+ "special": true
6429
  },
6430
  "128800": {
6431
  "content": "<|fim▁hole|>",
 
6549
  }
6550
  },
6551
  "bos_token": "<|begin▁of▁sentence|>",
6552
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{{'<|Assistant|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}",
6553
  "clean_up_tokenization_spaces": false,
6554
  "eos_token": "<|end▁of▁sentence|>",
6555
  "extra_special_tokens": {},
6556
  "legacy": true,
6557
+ "model_max_length": 131072,
6558
  "pad_token": "<|end▁of▁sentence|>",
6559
  "sp_model_kwargs": {},
6560
  "tokenizer_class": "LlamaTokenizer",