Upload 3 files
Browse files- README.md +34 -3
- config.json +28 -1
- hash_record_sha256.json +4 -0
README.md
CHANGED
@@ -1,3 +1,34 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
inference: false
|
4 |
+
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
5 |
+
base_model_relation: quantized
|
6 |
+
tags: [green, llmware-chat, p7, gguf, emerald]
|
7 |
+
---
|
8 |
+
|
9 |
+
# qwen2.5-coder-7b-instruct-gguf
|
10 |
+
|
11 |
+
**qwen2.5-coder-7b-instruct-gguf** is a GGUF Q4_K_M int4 quantized version of [Qwen2.5-Coder-7B-Instruct](https://www.huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct), providing a fast inference implementation, optimized for AI PCs.
|
12 |
+
|
13 |
+
This is from the latest release series from Qwen, and is an excellent chat/instruct coding assistant model.
|
14 |
+
|
15 |
+
### Model Description
|
16 |
+
|
17 |
+
- **Developed by:** Qwen
|
18 |
+
- **Quantized by:** llmware
|
19 |
+
- **Model type:** qwen2.5
|
20 |
+
- **Parameters:** 7 billion
|
21 |
+
- **Model Parent:** Qwen/Qwen2.5-Coder-7B-Instruct
|
22 |
+
- **Language(s) (NLP):** English
|
23 |
+
- **License:** Apache 2.0
|
24 |
+
- **Uses:** Chat, general-purpose LLM
|
25 |
+
- **Quantization:** int4
|
26 |
+
|
27 |
+
|
28 |
+
## Model Card Contact
|
29 |
+
|
30 |
+
[llmware on github](https://www.github.com/llmware-ai/llmware)
|
31 |
+
|
32 |
+
[llmware on hf](https://www.huggingface.co/llmware)
|
33 |
+
|
34 |
+
[llmware website](https://www.llmware.ai)
|
config.json
CHANGED
@@ -1 +1,28 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 28,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"transformers_version": "4.45.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 152064
|
28 |
+
}
|
hash_record_sha256.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Qwen2.5.1-Coder-7B-Instruct-Q4_K_M.gguf": "5e646e684063d4f3d6512fa9c895b05eaee22ad73b8d19e50518de656ff018e1",
|
3 |
+
"time_stamp": "2025-02-08_153147"
|
4 |
+
}
|