3thn commited on
Commit
cf477e7
1 Parent(s): 33ae5c5

02ff3823e4c5de4b768947b0589624fb98e007d9391a026e6d75c576b15b1423

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - generated_from_trainer
5
+ - axolotl
6
+ - mlx
7
+ base_model: Qwen/Qwen2-72B
8
+ datasets:
9
+ - cognitivecomputations/Dolphin-2.9
10
+ - teknium/OpenHermes-2.5
11
+ - m-a-p/CodeFeedback-Filtered-Instruction
12
+ - cognitivecomputations/dolphin-coder
13
+ - cognitivecomputations/samantha-data
14
+ - microsoft/orca-math-word-problems-200k
15
+ - Locutusque/function-calling-chatml
16
+ - internlm/Agent-FLAN
17
+ license_name: tongyi-qianwen
18
+ license_link: https://huggingface.co/Qwen/Qwen1.5-110B/blob/main/LICENSE
19
+ ---
20
+
21
+ # mlx-community/dolphin-2.9.2-qwen2-72b-4bit
22
+ This model was converted to MLX format from [`cognitivecomputations/dolphin-2.9.2-qwen2-72b`]() using mlx-lm version **0.12.1**.
23
+ Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-72b) for more details on the model.
24
+ ## Use with mlx
25
+
26
+ ```bash
27
+ pip install mlx-lm
28
+ ```
29
+
30
+ ```python
31
+ from mlx_lm import load, generate
32
+
33
+ model, tokenizer = load("mlx-community/dolphin-2.9.2-qwen2-72b-4bit")
34
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
35
+ ```
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151645,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 8192,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 29568,
11
+ "max_position_embeddings": 131072,
12
+ "max_window_layers": 28,
13
+ "model_type": "qwen2",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 80,
16
+ "num_key_value_heads": 8,
17
+ "quantization": {
18
+ "group_size": 64,
19
+ "bits": "4"
20
+ },
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "sliding_window": 4096,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.40.2",
27
+ "use_cache": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 152064
30
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff