Hugging Face's logo

Tesleum
/
0xCoder

Text Generation
Transformers
Safetensors
gpt_oss
Claude
Fable
Antropic
Agent
Ollama
vLLM
mxfp4
quantization
Mixture of Experts
conversational
Eval Results (legacy)
8-bit precision
Model card Files
xet
 Community
stevelionheart commited on
Commit
62509c8
·
verified ·
1 Parent(s): a6fab4b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -23,7 +23,7 @@ library_name: transformers
23
 
24
  # This structures your data into Hugging Face's official widget database
25
  model-index:
26
- - name: Claude-OSS
27
  results:
28
  - task:
29
  type: text-generation
@@ -39,7 +39,7 @@ model-index:
39
  value: "MXFP4 (Microscaling 4-bit)"
40
  ---
41
 
42
- # 📝 Claude-OSS (Fable 5)
43
 
44
  > [!NOTE]
45
  > **Hugging Face Metadata:** The automated metadata tag at the top of this page miscalculates this model as a 12B BF16/U8 model because the Hub parser cannot natively calculate the 32-expert MoE layout of `Claude-OSS`. The actual model size is **21B parameters** running natively on **MXFP4 microquantization**.
@@ -64,7 +64,7 @@ Open-Source OpenAI model powered by Claude Fable 5 Agent
64
 
65
  ## Transformers
66
 
67
- You can use `Claude-OSS` with Transformers. If you use the Transformers chat template, it will automatically apply the [harmony response format](https://github.com/openai/harmony). If you use `model.generate` directly, you need to apply the harmony format manually using the chat template or use our [openai-harmony](https://github.com/openai/harmony) package.
68
 
69
  To get started, install the necessary dependencies to setup your environment:
70
 
@@ -78,7 +78,7 @@ Once, setup you can proceed to run the model by running the snippet below:
78
  from transformers import pipeline
79
  import torch
80
 
81
- model_id = "Tesleum/Claude-OSS"
82
 
83
  pipe = pipeline(
84
  "text-generation",
@@ -102,7 +102,7 @@ Alternatively, you can run the model via [`Transformers Serve`](https://huggingf
102
 
103
  ```
104
  transformers serve
105
- transformers chat localhost:8000 --model-name-or-path Tesleum/Claude-OSS
106
  ```
107
 
108
  ## vLLM
@@ -113,7 +113,7 @@ vLLM recommends using [uv](https://docs.astral.sh/uv/) for Python dependency man
113
  curl -X POST "http://localhost:8000/v1/chat/completions" \
114
  -H "Content-Type: application/json" \
115
  --data '{
116
- "model": "Tesleum/Claude-OSS",
117
  "messages": [
118
  {
119
  "role": "user",
@@ -122,13 +122,13 @@ curl -X POST "http://localhost:8000/v1/chat/completions" \
122
  ]
123
  }'
124
 
125
- vllm serve "Tesleum/Claude-OSS"
126
  ```
127
 
128
  ## Docker
129
 
130
  ```bash
131
- docker model run hf.co/Tesleum/Claude-OSS
132
  ```
133
  ## Ollama
134
 
@@ -152,7 +152,7 @@ The reasoning level can be set in the system prompts, e.g., "Reasoning: high".
152
 
153
  # Tool use
154
 
155
- The claude-oss models are excellent for:
156
  * Agentic operations like browser tasks
157
  * Function calling with defined schemas
158
  * Web browsing (using built-in browsing tools)
 
23
 
24
  # This structures your data into Hugging Face's official widget database
25
  model-index:
26
+ - name: 0xCoder
27
  results:
28
  - task:
29
  type: text-generation
 
39
  value: "MXFP4 (Microscaling 4-bit)"
40
  ---
41
 
42
+ # 📝 0xCoder (Fable 5)
43
 
44
  > [!NOTE]
45
  > **Hugging Face Metadata:** The automated metadata tag at the top of this page miscalculates this model as a 12B BF16/U8 model because the Hub parser cannot natively calculate the 32-expert MoE layout of `Claude-OSS`. The actual model size is **21B parameters** running natively on **MXFP4 microquantization**.
 
64
 
65
  ## Transformers
66
 
67
+ You can use `0xCoder` with Transformers. If you use the Transformers chat template, it will automatically apply the [harmony response format](https://github.com/openai/harmony). If you use `model.generate` directly, you need to apply the harmony format manually using the chat template or use our [openai-harmony](https://github.com/openai/harmony) package.
68
 
69
  To get started, install the necessary dependencies to setup your environment:
70
 
 
78
  from transformers import pipeline
79
  import torch
80
 
81
+ model_id = "Tesleum/0xCoder"
82
 
83
  pipe = pipeline(
84
  "text-generation",
 
102
 
103
  ```
104
  transformers serve
105
+ transformers chat localhost:8000 --model-name-or-path Tesleum/0xCoder
106
  ```
107
 
108
  ## vLLM
 
113
  curl -X POST "http://localhost:8000/v1/chat/completions" \
114
  -H "Content-Type: application/json" \
115
  --data '{
116
+ "model": "Tesleum/0xCoder",
117
  "messages": [
118
  {
119
  "role": "user",
 
122
  ]
123
  }'
124
 
125
+ vllm serve "Tesleum/0xCoder"
126
  ```
127
 
128
  ## Docker
129
 
130
  ```bash
131
+ docker model run hf.co/Tesleum/0xCoder
132
  ```
133
  ## Ollama
134
 
 
152
 
153
  # Tool use
154
 
155
+ The 0xCoder models are excellent for:
156
  * Agentic operations like browser tasks
157
  * Function calling with defined schemas
158
  * Web browsing (using built-in browsing tools)