Skip to content

Commit

Permalink
FEAT: Add qwen2.5-coder 0.5B 1.5B 3B 14B 32B (#2543)
Browse files Browse the repository at this point in the history
  • Loading branch information
@frostyplanet
frostyplanet authored Nov 13, 2024
1 parent fe94552 commit 38728b6
Show file tree
Hide file tree
Showing 2 changed files with 387 additions and 4 deletions.
180 changes: 176 additions & 4 deletions xinference/model/llm/llm_family.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8205,6 +8205,16 @@
],
"model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": "0_5",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-0.5B"
},
{
"model_format": "pytorch",
"model_size_in_billions": "1_5",
Expand All @@ -8213,8 +8223,17 @@
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-1.5B",
"model_revision": "d3586cfe793730945f8e4d7ef31032a3ee50247d"
"model_id": "Qwen/Qwen2.5-Coder-1.5B"
},
{
"model_format": "pytorch",
"model_size_in_billions": "3",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-3B"
},
{
"model_format": "pytorch",
Expand All @@ -8224,8 +8243,27 @@
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-7B",
"model_revision": "30b6a7e874a78d46b80fa1db3194ea427dd41b08"
"model_id": "Qwen/Qwen2.5-Coder-7B"
},
{
"model_format": "pytorch",
"model_size_in_billions": 14,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-14B"
},
{
"model_format": "pytorch",
"model_size_in_billions": 32,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-32B"
}
]
},
Expand All @@ -8243,6 +8281,16 @@
],
"model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": "0_5",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-0.5B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": "1_5",
Expand All @@ -8253,6 +8301,16 @@
],
"model_id": "Qwen/Qwen2.5-Coder-1.5B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": "3",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-3B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": 7,
Expand All @@ -8263,6 +8321,53 @@
],
"model_id": "Qwen/Qwen2.5-Coder-7B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": 14,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-14B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": 32,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
},
{
"model_format": "gptq",
"model_size_in_billions": "0_5",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "1_5",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "3",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "7",
Expand All @@ -8272,6 +8377,73 @@
],
"model_id": "Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "14",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "32",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "awq",
"model_size_in_billions": "0_5",
"quantizations": [
"Int4"
],
"model_id": "Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ"
},
{
"model_format": "awq",
"model_size_in_billions": "1_5",
"quantizations": [
"Int4"
],
"model_id": "Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ"
},
{
"model_format": "awq",
"model_size_in_billions": "3",
"quantizations": [
"Int4"
],
"model_id": "Qwen/Qwen2.5-Coder-3B-Instruct-AWQ"
},
{
"model_format": "awq",
"model_size_in_billions": "7",
"quantizations": [
"Int4"
],
"model_id": "Qwen/Qwen2.5-Coder-7B-Instruct-AWQ"
},
{
"model_format": "awq",
"model_size_in_billions": "14",
"quantizations": [
"Int4"
],
"model_id": "Qwen/Qwen2.5-Coder-14B-Instruct-AWQ"
},
{
"model_format": "awq",
"model_size_in_billions": "32",
"quantizations": [
"Int4"
],
"model_id": "Qwen/Qwen2.5-Coder-32B-Instruct-AWQ"
},

{
"model_format": "ggufv2",
"model_size_in_billions": "1_5",
Expand Down
Loading

0 comments on commit 38728b6

Please sign in to comment.