German Abramov commited on
Commit
7b1ce07
·
1 Parent(s): 13e47b3

added ckpt

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,74 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ base_model: t-tech/T-pro-it-2.0
5
+ tags:
6
+ - llama-cpp
7
+ - gguf
8
+ license: apache-2.0
9
+ ---
10
+
11
+ # T-pro-it-2.0-GGUF
12
+
13
+ **🚨 Users are advised to exercise caution and are responsible for any additional training and oversight required to ensure the model's responses meet acceptable ethical and safety standards. The responsibility for incorporating this model into industrial or commercial solutions lies entirely with those who choose to deploy it.**
14
+
15
+
16
+ This repository contains **T-pro-it-2.0** converted to the **GGUF** format with
17
+ [llama.cpp](https://github.com/ggerganov/llama.cpp).
18
+ See the original BF16 model here: [t-tech/T-pro-it-2.0](https://huggingface.co/t-tech/T-pro-it-2.0).
19
+
20
+
21
+ ## 📊 Benchmarks
22
+
23
+ TBD
24
+
25
+ ## Available quantisations
26
+
27
+ > **Recommendation:** choose the **highest-quality quantisation that fits your hardware** (VRAM / RAM).
28
+
29
+ | Filename (→ `-gguf`) | Quant method | Bits | Size (GB) |
30
+ |----------------------|--------------|------|-----------|
31
+ | `t-pro-it-2.0-q2_k` | Q2_K | 2 | 12.3 |
32
+ | `t-pro-it-2.0-iq3_xs` | IQ3_XS | 3 | 13.7 |
33
+ | `t-pro-it-2.0-iq3_s` | IQ3_S | 3 | 14.4 |
34
+ | `t-pro-it-2.0-q3_k_s` | Q3_K_S | 3 | 14.4 |
35
+ | `t-pro-it-2.0-q3_k_m` | Q3_K_M | 3 | 16.0 |
36
+ | `t-pro-it-2.0-iq4_xs` | IQ4_XS | 4 | 17.9 |
37
+ | `t-pro-it-2.0-q4_k_s` | Q4_K_S | 4 | 18.8 |
38
+ | `t-pro-it-2.0-iq4_nl` | IQ4_NL | 4 | 18.8 |
39
+ | `t-pro-it-2.0-q4_0` | Q4_0 | 4 | 18.6 |
40
+ | `t-pro-it-2.0-q4_k_m` | Q4_K_M | 4 | 19.8 |
41
+ | `t-pro-it-2.0-q5_k_s` | Q5_K_S | 5 | 22.6 |
42
+ | `t-pro-it-2.0-q5_0` | Q5_0 | 5 | 22.6 |
43
+ | `t-pro-it-2.0-q5_k_m` | Q5_K_M | 5 | 23.2 |
44
+ | `t-pro-it-2.0-q6_k` | Q6_K | 6 | 26.9 |
45
+ | `t-pro-it-2.0-q8_0` | Q8_0 | 8 | 34.8 |
46
+
47
+ *Size figures assume **no GPU off-loading**. Off-loading lowers RAM usage and uses VRAM instead.*
48
+
49
+ ## Quickstart
50
+
51
+ ### llama.cpp
52
+
53
+ Check out our [llama.cpp documentation](https://qwen.readthedocs.io/en/latest/run_locally/llama.cpp.html) for more usage guide.
54
+
55
+ We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and install it following the official guide. We follow the latest version of llama.cpp.
56
+ In the following demonstration, we assume that you are running commands under the repository `llama.cpp`.
57
+
58
+ ```shell
59
+ ./llama-cli -hf t-tech/T-pro-it-2.0-GGUF:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --presence-penalty 1.0 -c 40960 -n 32768 --no-context-shift
60
+ ```
61
+
62
+ ### ollama
63
+
64
+ Check out our [ollama documentation](https://qwen.readthedocs.io/en/latest/run_locally/ollama.html) for more usage guide.
65
+
66
+ You can run Qwen3 with one command:
67
+
68
+ ```shell
69
+ ollama run hf.co/t-tech/T-pro-it-2.0-GGUF:Q8_0
70
+ ```
71
+
72
+ ## Switching Between Thinking and Non-Thinking Mode
73
+
74
+ You can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
T-pro-it-2.0-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6c97c0df69b2cf7a0a7ee2ccd5adab8b73daf8a982493d30faeabab56bf8e0
3
+ size 14433952768
T-pro-it-2.0-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172494c8ff379bc0b3f3b2bf6a13ea3e5d635c8f3b343472cb32591eea4054ee
3
+ size 13702571008
T-pro-it-2.0-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9bed6962664c43977d0ec7c170f0fc9cdb19672e44db19c1e47c0b3b151888b
3
+ size 18810034208
T-pro-it-2.0-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2da2db6f442fbd356bf0a0ee10a76f19960e68fac7a0adf2a8786577de4b00
3
+ size 17853845408
T-pro-it-2.0-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6fc159672ec341cef0e1ce902a48b75e2f4ae2b73b1253f4a05496f4aeca46
3
+ size 12344440928
T-pro-it-2.0-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988374f9690e90cc7fe4a828a77abf682423325ea4502c4ddfce50fb27626690
3
+ size 15971427328
T-pro-it-2.0-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc4806e7c668f01ed5c83a8306aea406fa8bb61aeddc51fce6818df6eeb6686
3
+ size 14389388288
T-pro-it-2.0-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429390d00e0eacc984acc315c77b9f7d13658ad12b53188735af481ce39d8935
3
+ size 18637019168
T-pro-it-2.0-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bddc87e6faa91fc234d431ee8988f4884c31ecbf857ac655f3962892f7f6432
3
+ size 19761616928
T-pro-it-2.0-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69736c033d2cd49b2a3e89404a0d4af777526cc3371634be3d65cc65fb945cb
3
+ size 18770712608
T-pro-it-2.0-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658390643d87d2f751f386ff62b6e159e930fa455ddab6a7fed750afa55e30d7
3
+ size 22634789408
T-pro-it-2.0-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5145c5a4dd93b3418eb2c79effc13fced38fba6e62735fb6cd4d3fe55147e51f
3
+ size 23214127648
T-pro-it-2.0-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a528cff7655153bcc04320798d871dce3dd3abeac5d6ba70c9a2e2c447940b
3
+ size 22634789408
T-pro-it-2.0-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2499484f2cbf7bcc62e7885677681d86e1482f202b4cb9e4a38d8b3f93a309
3
+ size 26882420288
T-pro-it-2.0-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f78c91aa9103b4611000bbaa5ce9dcae462f4d76ad376f0ae53f3355af6022
3
+ size 34816168448